© 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. 27703
    Prev
    Next
    INDEX
    Explanations

    number parameter array guaranteed

    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
    iad
    -0.09
    ronic
    -0.08
    adeiras
    -0.08
    heimer
    -0.08
    ogna
    -0.08
     Lup
    -0.07
    å¾Īå¿«çļĦ
    -0.07
    adeira
    -0.07
    ÙĨداÙĨ
    -0.07
    espóÅĤ
    -0.07
    POSITIVE LOGITS
     output
    0.08
    è¾ĵåĩº
    0.07
    建ä¸ļ
    0.07
    _ret
    0.07
    è¾ĵåĩºçļĦ
    0.07
    igor
    0.07
    inken
    0.07
     Returned
    0.07
    欣
    0.07
    輸åĩº
    0.06
    Activations Density 0.007%

    No Known Activations