© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 19-RESID-POST-AA
    11. 120809
    Prev
    Next
    INDEX
    Explanations

    Food and nutrition

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    툴
    -0.07
    <|im_end|>
    -0.07
    assen
    -0.07
     utilizar
    -0.07
     computer
    -0.06
     muscle
    -0.06
    로서
    -0.06
    عب
    -0.06
    创业
    -0.06
    積
    -0.06
    POSITIVE LOGITS
     Dominion
    0.08
    REDENTIAL
    0.07
     Başbakan
    0.07
    귱
    0.07
    혭
    0.07
    .Wait
    0.07
    .Remove
    0.07
    LoginPage
    0.07
    <tool_call>
    0.07
    婉
    0.07
    Activations Density 0.019%

    No Known Activations