© 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. 50308
    Prev
    Next
    INDEX
    Explanations

    Jokes

    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
     Africa
    -0.07
    每次都
    -0.06
     his
    -0.06
    affen
    -0.06
     Cu
    -0.06
     silver
    -0.06
     Ink
    -0.06
    ū
    -0.06
    invest
    -0.06
    antt
    -0.06
    POSITIVE LOGITS
    ɷ
    0.08
    的区别
    0.08
     Shuttle
    0.07
     NSDictionary
    0.07
    讽
    0.07
    缈
    0.07
     Bishop
    0.07
    整形
    0.07
     الدفاع
    0.07
    ⟱
    0.07
    Activations Density 0.002%

    No Known Activations