© 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. 14312
    Prev
    Next
    INDEX
    Explanations

    command-line interface

    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
    st
    -0.06
    мки
    -0.06
    ung
    -0.06
     entorno
    -0.06
    çŀ
    -0.06
    gl
    -0.06
    stand
    -0.06
    ube
    -0.05
    Specifier
    -0.05
    æĹ©å¹´
    -0.05
    POSITIVE LOGITS
    Ctx
    0.08
     isSuccess
    0.08
    oods
    0.08
    agate
    0.08
    utors
    0.08
    idio
    0.08
    OMIC
    0.08
    è²łåĤµ
    0.08
    fras
    0.08
    UTT
    0.08
    Activations Density 0.004%

    No Known Activations