© 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. 99996
    Prev
    Next
    INDEX
    Explanations

    python imports

    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
    �
    -0.09
    Franc
    -0.08
    �
    -0.08
     writeTo
    -0.07
    筑牢
    -0.07
    .storage
    -0.07
     Cros
    -0.07
    䲢
    -0.07
    �
    -0.07
    急诊
    -0.07
    POSITIVE LOGITS
    ALCHEMY
    0.07
    ˤ
    0.07
    (Of
    0.07
     рейтинг
    0.07
    .reactivex
    0.07
    奠基
    0.07
    천
    0.07
    noteq
    0.06
    ety
    0.06
    kf
    0.06
    Activations Density 0.002%

    No Known Activations