© 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. 70102
    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
    Negative Logits
    /print
    -0.07
    Modificar
    -0.07
    ksi
    -0.07
     peninsula
    -0.07
     '#{
    -0.06
    实验
    -0.06
    Sold
    -0.06
    辛辣
    -0.06
    公告称
    -0.06
     cannons
    -0.06
    POSITIVE LOGITS
     الصادر
    0.09
     customary
    0.08
    愉
    0.08
    _confirmation
    0.08
    师范
    0.07
     Explanation
    0.07
    在一个
    0.07
    -rate
    0.07
    (Syntax
    0.07
     consistent
    0.07
    Activations Density 0.022%

    No Known Activations