© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 82558
    Prev
    Next
    INDEX
    Explanations

    opinions and discussions

    np_max-act · gemini-2.0-flash

    statements or discussions that convey or analyze discriminatory, sexist/misogynistic, or otherwise harmful rhetoric and laws toward marginalized groups, often in religious or historical contexts.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     вн
    -0.07
     street
    -0.07
    榈
    -0.07
    置换
    -0.07
    >

↵
    -0.06
    洞察
    -0.06
     tüket
    -0.06
     '';↵↵
    -0.06
     cyt
    -0.06
    תחיל
    -0.06
    POSITIVE LOGITS
    QUE
    0.07
    ()%
    0.07
    זי
    0.06
     Hicks
    0.06
    腻
    0.06
    小龙
    0.06
     глаз
    0.06
    ,R
    0.06
    İZ
    0.06
    首领
    0.06
    Activations Density 0.162%

    No Known Activations