© 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. 15-RESID-POST-AA
    11. 5400
    Prev
    Next
    INDEX
    Explanations

    rankings

    np_max-act · gemini-2.0-flash
    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
     Eisen
    -0.07
     Wiley
    -0.06
     Renewable
    -0.06
    枭
    -0.06
     his
    -0.06
     rag
    -0.06
    �
    -0.06
     SUMMARY
    -0.06
    cc
    -0.06
     bass
    -0.06
    POSITIVE LOGITS
     وخ
    0.07
     Серг
    0.07
     questioned
    0.07
     yüz
    0.06
    经销
    0.06
    _Q
    0.06
    .after
    0.06
    处分
    0.06
     throwError
    0.06
    份
    0.06
    Activations Density 0.059%

    No Known Activations