© 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. 45279
    Prev
    Next
    INDEX
    Explanations

    protocol buffer compiler

    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
    azzo
    -0.08
    obiet
    -0.07
    olé
    -0.07
    cito
    -0.07
    angeb
    -0.07
     INFOR
    -0.07
     Thạnh
    -0.07
    stype
    -0.07
    .windows
    -0.07
    ozo
    -0.07
    POSITIVE LOGITS
    abay
    0.08
     exp
    0.07
    åľ¨æ³ķå¾ĭ
    0.07
    HOOK
    0.07
    ãģı
    0.07
    èĢ¦
    0.07
    exp
    0.06
    íĮĮ
    0.06
    zi
    0.06
    è¾ĥ为
    0.06
    Activations Density 0.003%

    No Known Activations