© 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. 39826
    Prev
    Next
    INDEX
    Explanations

    records, archive, storage

    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
    åIJģ
    -0.08
    é¢Ŀ
    -0.07
    çĵ¢
    -0.07
    é¡į
    -0.07
    rop
    -0.07
    elh
    -0.06
    rops
    -0.06
    è¡¥ç»Ļ
    -0.06
     бÑĢи
    -0.06
     капелÑĮ
    -0.06
    POSITIVE LOGITS
    å½Ĵæ¡£
    0.13
    ä¿Ŀ管
    0.13
    åŃĺåĤ¨
    0.13
    çķĻåŃĺ
    0.12
    ä¿ĿåŃĺ
    0.12
     storage
    0.12
    /archive
    0.12
     storing
    0.12
     Storage
    0.11
    storage
    0.11
    Activations Density 0.065%

    No Known Activations