© 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. 11-RESID-POST-AA
    11. 83365
    Prev
    Next
    INDEX
    Explanations

    Code special characters

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    のか
    -0.07
    .make
    -0.07
    えない
    -0.07
    ய
    -0.07
    สามาร
    -0.07
     midway
    -0.07
    路程
    -0.07
    umbs
    -0.07
     Radiation
    -0.06
    仲裁
    -0.06
    POSITIVE LOGITS
     bored
    0.07
    _MIX
    0.06
    OV
    0.06
    清洗
    0.06
     boring
    0.06
     vanilla
    0.06
     unlimited
    0.06
    inv
    0.06
     decent
    0.06
    屃
    0.06
    Activations Density 0.001%

    No Known Activations