© 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. 5446
    Prev
    Next
    INDEX
    Explanations

    disclosure

    np_max-act · gemini-2.0-flash

    words or verb forms indicating past actions (past-tense/past-participle verbs).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
    Not in Any Lists

    No Comments

    Negative Logits
    Ab
    -0.07
    _WRONG
    -0.07
    oh
    -0.07
     avait
    -0.07
    _op
    -0.07
    (do
    -0.07
    _emp
    -0.07
     is
    -0.07
     investigations
    -0.06
     zijn
    -0.06
    POSITIVE LOGITS
    การออกแบบ
    0.07
     FlatButton
    0.06
    传授
    0.06
    .setTime
    0.06
    特点是
    0.06
    CardContent
    0.06
    淡化
    0.06
     Historic
    0.06
    建立起
    0.06
    强大
    0.06
    Activations Density 1.477%

    No Known Activations