© 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. 72135
    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
    ברה
    -0.07
    (defvar
    -0.07
    (forms
    -0.07
     porrf
    -0.07
    -bot
    -0.07
     автомоб
    -0.07
    GV
    -0.07
    重金属
    -0.07
    _FACTORY
    -0.07
     Bron
    -0.07
    POSITIVE LOGITS
     самые
    0.07
    绪
    0.07
    ﻏ
    0.07
    。',↵
    0.07
    何况
    0.07
    ẹ
    0.07
     مكان
    0.06
    具体
    0.06
     cười
    0.06
     قائلا
    0.06
    Activations Density 0.185%

    No Known Activations