© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63800
    Prev
    Next
    INDEX
    Explanations

    node, factory, code, items, story

    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
    ernel
    -0.08
    -0.08
    reau
    -0.07
    StrictEqual
    -0.07
    eux
    -0.07
    гами
    -0.07
     ///</
    -0.07
    à¸ģา
    -0.07
    ords
    -0.07
    urning
    -0.07
    POSITIVE LOGITS
    è¿ĺæľīå¾ħ
    0.07
     nata
    0.07
    tel
    0.07
    tod
    0.06
    odel
    0.06
    cean
    0.06
     spons
    0.06
    ç¢Į
    0.06
    SEE
    0.06
    farm
    0.06
    Activations Density 0.091%

    No Known Activations