© 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. 13592
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    alaman
    -0.08
    agos
    -0.08
    å¢ŀæ®ĸ
    -0.07
    ës
    -0.07
    acz
    -0.07
     myster
    -0.07
    æ½
    -0.07
    ело
    -0.07
    anca
    -0.07
    ilian
    -0.07
    POSITIVE LOGITS
    пина
    0.06
    AdapterFactory
    0.06
    ä¸ŃåĽ½åĽ½éĻħ
    0.06
    erti
    0.06
    ä¸İåĽ½éĻħ
    0.06
    °
    0.06
    rel
    0.06
    èĭ¥æĺ¯
    0.06
    ;!
    0.06
    reet
    0.06
    Activations Density 0.055%

    No Known Activations