© 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. 71634
    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
    用药
    -0.07
    ENOMEM
    -0.07
    チョ
    -0.07
     schl
    -0.07
    骉
    -0.06
     слиш
    -0.06
    营地
    -0.06
    FDA
    -0.06
     pokemon
    -0.06
     RSA
    -0.06
    POSITIVE LOGITS
     legitim
    0.07
     שאין
    0.07
    家喻户
    0.07
    (cc
    0.07
    ➠
    0.06
    游戏代练
    0.06
    lic
    0.06
    再造
    0.06
     yı
    0.06
    〉
    0.06
    Activations Density 0.060%

    No Known Activations