© 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. 107277
    Prev
    Next
    INDEX
    Explanations

    y

    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
    💐
    -0.08
     Unique
    -0.08
    非常好的
    -0.07
     MODIFY
    -0.07
    百分百
    -0.07
    ORB
    -0.07
     ''){↵
    -0.07
     ntohs
    -0.07
    UICollectionView
    -0.07
    Tell
    -0.07
    POSITIVE LOGITS
    tag
    0.07
     rage
    0.07
     protesting
    0.07
    eb
    0.06
     strides
    0.06
     asbestos
    0.06
    进了
    0.06
     Marino
    0.06
    .tests
    0.06
    整治
    0.06
    Activations Density 0.006%

    No Known Activations