© 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. 19-RESID-POST-AA
    11. 50757
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    dn
    -0.07
    pell
    -0.07
    婠
    -0.07
    winner
    -0.07
    lore
    -0.06
    dance
    -0.06
    火力
    -0.06
    נצי
    -0.06
    秾
    -0.06
    _common
    -0.06
    POSITIVE LOGITS
    捌
    0.09
     Chiến
    0.07
    _UUID
    0.07
     environmental
    0.07
     несколько
    0.07
    _DP
    0.07
     исп
    0.07
     partnering
    0.07
     transformative
    0.07
    _tp
    0.07
    Activations Density 0.039%

    No Known Activations