© 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. 30274
    Prev
    Next
    INDEX
    Explanations

    network protocol suite

    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
    inkel
    -0.08
    ủng
    -0.08
    иÑģк
    -0.07
    chair
    -0.07
    转载请
    -0.07
    ugi
    -0.07
     Lust
    -0.07
     manch
    -0.07
    utherland
    -0.07
     %-
    -0.07
    POSITIVE LOGITS
    Id
    0.06
    åĽĬæĭ¬
    0.06
    ossed
    0.06
     punt
    0.06
    ç«ĭå¿Ĺ
    0.06
     dim
    0.06
    ver
    0.06
    çŃ
    0.06
     fault
    0.06
    ur
    0.06
    Activations Density 0.109%

    No Known Activations