© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 64456
    Prev
    Next
    INDEX
    Explanations

    mentions or subparts of the word "adenocarcinoma" (the adenocarcinoma histologic subtype).

    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
    (request
    -0.07
    KV
    -0.07
     TRUE
    -0.07
    صر
    -0.07
    _cnt
    -0.07
    谁
    -0.07
    冲
    -0.07
    (cnt
    -0.07
    战争
    -0.06
    Pag
    -0.06
    POSITIVE LOGITS
    /menu
    0.07
    .dist
    0.07
    attered
    0.07
    העבר
    0.07
     maté
    0.07
     제품
    0.07
     Maker
    0.06
    Specifications
    0.06
     Sevent
    0.06
    עובד
    0.06
    Activations Density 0.001%

    No Known Activations