© 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. 4134
    Prev
    Next
    INDEX
    Explanations

    longer

    np_max-act · gemini-2.0-flash

    specialized scientific or technical jargon and acronyms, especially hyphenated or all-caps terms common in biomedical and engineering 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
    .↵
    -0.16
    .↵↵
    -0.15
    .
    -0.14
    。↵
    -0.14
    ?↵↵
    -0.12
    ↵↵
    -0.12
    ↵
    -0.10
    .↵↵↵
    -0.10
    。↵↵
    -0.10
    )↵
    -0.10
    POSITIVE LOGITS
    6
    0.08
    .down
    0.07
     الوطني
    0.07
    4
    0.07
    ᛏ
    0.06
    .pt
    0.06
    3
    0.06
    �
    0.06
     rouge
    0.06
    捏
    0.06
    Activations Density 14.582%

    No Known Activations