© 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. 83461
    Prev
    Next
    INDEX
    Explanations

    Martha

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .ng
    -0.09
    胛
    -0.08
    澎湃
    -0.08
    BuildContext
    -0.07
    (paths
    -0.07
    ,cv
    -0.07
    恹
    -0.07
    分泌
    -0.07
     bilateral
    -0.07
    _BAND
    -0.07
    POSITIVE LOGITS
    łość
    0.07
     peaked
    0.07
     journalistic
    0.07
    :function
    0.07
    .Write
    0.07
     SET
    0.07
    \Factory
    0.07
    "];
↵
    0.06
     Answer
    0.06
     answer
    0.06
    Activations Density 0.002%

    No Known Activations