© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10658
    Prev
    Next
    INDEX
    Explanations

    section separators

    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
    大åIJį
    -0.07
    _WARNINGS
    -0.07
    åĵĪ
    -0.07
    imeline
    -0.07
     vard
    -0.07
    Parms
    -0.07
    luž
    -0.07
    stown
    -0.07
    ergestellt
    -0.07
    adow
    -0.07
    POSITIVE LOGITS
    zni
    0.07
    memberOf
    0.06
    rez
    0.06
    Ķ
    0.06
    åŃ
    0.06
    çŁ¥éŁ³
    0.06
    人æĿ¥
    0.06
    IJ
    0.06
    is
    0.06
    wiad
    0.06
    Activations Density 0.003%

    No Known Activations