© 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. 32162
    Prev
    Next
    INDEX
    Explanations

    series, graph, domain, numbers

    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
    imo
    -0.07
    åįĬ
    -0.07
    åĪļåĪļ好
    -0.06
    rans
    -0.06
    çĻ¾äºĭ
    -0.06
     fore
    -0.06
    _HALF
    -0.06
     saj
    -0.06
     cascade
    -0.06
    顺é£İ
    -0.06
    POSITIVE LOGITS
    giv
    0.09
    (any
    0.09
    人æĿ¥è¯´
    0.08
    engen
    0.08
    _ib
    0.08
    xfb
    0.08
     qualsiasi
    0.08
    pher
    0.07
     Anything
    0.07
    åIJįæĢĿ
    0.07
    Activations Density 0.026%

    No Known Activations