© 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. 62566
    Prev
    Next
    INDEX
    Explanations

    instantaneous

    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
    tsky
    -0.08
    icoli
    -0.08
    chants
    -0.08
    ستاÙĨ
    -0.08
    thest
    -0.08
    czy
    -0.08
    itian
    -0.08
    æĹ¥æ¸IJ
    -0.08
     задÑĥма
    -0.08
    icester
    -0.08
    POSITIVE LOGITS
    aneous
    0.17
    aneously
    0.13
    åį³éĢĿ
    0.11
    ä¸ĩåıĺ
    0.09
    à¸Ĺัà¸Ļ
    0.08
    orary
    0.07
    髦
    0.07
    loch
    0.07
    ledge
    0.07
    ly
    0.07
    Activations Density 0.013%

    No Known Activations