© 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. 72144
    Prev
    Next
    INDEX
    Explanations

    using only what's needed

    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
    äche
    -0.08
    裎
    -0.07
    clc
    -0.07
    厚
    -0.07
    つく
    -0.07
    훔
    -0.07
    RH
    -0.07
    ıp
    -0.07
     descricao
    -0.06
    亸
    -0.06
    POSITIVE LOGITS
    .guard
    0.07
    /core
    0.07
     contributes
    0.07
    STANCE
    0.07
    /article
    0.07
    സ
    0.06
    _setting
    0.06
    .JPanel
    0.06
    -S
    0.06
    (selected
    0.06
    Activations Density 0.072%

    No Known Activations