© 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. 19468
    Prev
    Next
    INDEX
    Explanations

    and followed by specific tokens

    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
    åĪ°èĢģ
    -0.07
    eix
    -0.07
    æĹģ
    -0.07
    请åIJĮåѦ们
    -0.07
    _mr
    -0.07
    NSS
    -0.07
    äºŃäºŃ
    -0.07
    UTA
    -0.07
    è°ĵ
    -0.07
    åĸ³åĸ³
    -0.06
    POSITIVE LOGITS
    asan
    0.07
     Trey
    0.07
    DV
    0.07
    azen
    0.07
    çĶľèľľçļĦ
    0.06
    éter
    0.06
    äººä¹Ł
    0.06
     Reeves
    0.06
    uspend
    0.06
    สามัà¸į
    0.06
    Activations Density 0.031%

    No Known Activations