© 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. 58566
    Prev
    Next
    INDEX
    Explanations

    /current or /latest

    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
    ogi
    -0.08
    _hdl
    -0.08
    лива
    -0.07
    anes
    -0.07
    osat
    -0.07
    ering
    -0.07
    ç±»çŃī
    -0.07
    upu
    -0.06
    undry
    -0.06
    -la
    -0.06
    POSITIVE LOGITS
    åĴĮæĹ¥æľ¬
    0.08
    寸
    0.07
    å¾ĹçĽĬ
    0.06
    ([^
    0.06
    ementer
    0.06
    彤
    0.06
    aupts
    0.06
    ÑħаниÑı
    0.06
    à¸Ķ
    0.06
    à¹ģà¸Ĺà¹ī
    0.06
    Activations Density 0.195%

    No Known Activations