© 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. 7-RESID-POST-AA
    11. 42640
    Prev
    Next
    INDEX
    Explanations

    academia

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     BMC
    -0.07
    ANGLES
    -0.07
    akeup
    -0.07
    '"↵
    -0.07
     eagle
    -0.07
    _GUID
    -0.07
     Prepare
    -0.07
    归属
    -0.07
     SUMMARY
    -0.07
    下一步
    -0.06
    POSITIVE LOGITS
    Expression
    0.07
    .processor
    0.07
     phạt
    0.07
     DTO
    0.07
    ých
    0.07
     Redemption
    0.07
    法
    0.07
     Colors
    0.06
    扂
    0.06
     mặc
    0.06
    Activations Density 0.006%

    No Known Activations