© 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. 128365
    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_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
    三项
    -0.08
     entitlement
    -0.08
     guide
    -0.07
    급
    -0.07
    درجة
    -0.07
     плохо
    -0.07
    uido
    -0.07
    脱离
    -0.07
    文娱
    -0.07
    听话
    -0.07
    POSITIVE LOGITS
    [df
    0.08
    <hr
    0.07
    _snapshot
    0.07
    假设
    0.07
    (rename
    0.07
    _pre
    0.07
    bn
    0.06
    அ
    0.06
    getContent
    0.06
    _NS
    0.06
    Activations Density 0.144%

    No Known Activations