© 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. 62455
    Prev
    Next
    INDEX
    Explanations

    data processing operations

    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
    chino
    -0.09
    stav
    -0.08
    æĦıæĢĿ
    -0.07
    æĪĸå°ij
    -0.07
    isas
    -0.07
    øv
    -0.07
    моÑĤÑĢов
    -0.07
    ä¸įåįķ
    -0.07
    etek
    -0.07
    ingin
    -0.07
    POSITIVE LOGITS
    _bulk
    0.07
    alm
    0.07
     raw
    0.07
     messy
    0.06
    éĤ¦
    0.06
     Flake
    0.06
    ugn
    0.06
     decl
    0.06
     conveniently
    0.06
    fil
    0.06
    Activations Density 0.006%

    No Known Activations