© 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. 70425
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    怎么可能
    -0.08
    迓
    -0.08
    甗
    -0.08
    ingt
    -0.07
     disrespect
    -0.07
    %),
    -0.07
    Ticker
    -0.07
    人大代表
    -0.07
     עשרות
    -0.07
    OPT
    -0.06
    POSITIVE LOGITS
     effet
    0.09
    冰淇淋
    0.07
     Esther
    0.07
     authorized
    0.07
     '/',
    0.07
     universe
    0.07
    实行
    0.07
     labeling
    0.07
    eting
    0.07
    王朝
    0.07
    Activations Density 0.000%

    No Known Activations