© 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. 60914
    Prev
    Next
    INDEX
    Explanations

    question punctuation and question-form phrases, especially occurrences of “?” in prose or code (including parenthetical or inline questions).

    oai_token-act-pair · gpt-5Triggered 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
    =edge
    -0.08
    裛
    -0.08
     iş
    -0.08
     of
    -0.08
    окумент
    -0.08
    �
    -0.07
    ORIGINAL
    -0.07
    屣
    -0.07
    rest
    -0.07
    INavigationController
    -0.07
    POSITIVE LOGITS
    ?
    0.10
    ?↵↵
    0.07
    ?>↵
    0.07
    ?↵
    0.07
     jego
    0.07
    苉
    0.06
    etine
    0.06
    chten
    0.06
     "?
    0.06
     silicone
    0.06
    Activations Density 0.295%

    No Known Activations