© 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 EvalsExportsAPI 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. 15951
    Prev
    Next
    INDEX
    Explanations

    medical conditions

    np_max-act · gemini-2.0-flash

    comma-separated or parenthetical lists that enumerate domain-specific items (e.g., symptoms, products, languages) within a sentence.

    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
    ϝ
    -0.09
    器具
    -0.08
    草案
    -0.08
    담
    -0.07
    _Default
    -0.07
    种子
    -0.07
    疏散
    -0.07
    然後
    -0.07
     Mohammad
    -0.07
    大夫
    -0.07
    POSITIVE LOGITS
     ZIP
    0.06
    cased
    0.06
     şik
    0.06
     mattered
    0.06
     am
    0.06
    yield
    0.06
    NIL
    0.06
    meye
    0.06
     unreliable
    0.06
    performance
    0.06
    Activations Density 21.280%

    No Known Activations