© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33856
    Prev
    Next
    INDEX
    Explanations

    hooks, methodology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OwnProperty
    -0.08
    HTTPHeader
    -0.07
    临å®ī
    -0.07
    .azure
    -0.07
    erial
    -0.07
     $('[
    -0.07
    itious
    -0.07
    ок
    -0.07
    è¿Ļä¹Īå¤ļ人
    -0.07
    ading
    -0.07
    POSITIVE LOGITS
    UIL
    0.07
    åłĤ
    0.07
    0.06
    äºĶèĬ±
    0.06
    èĶļ
    0.06
    å¼Ł
    0.06
    å±ī
    0.06
    bile
    0.06
    åݦ
    0.06
    é¢ĸ
    0.06
    Activations Density 0.009%

    No Known Activations