© 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. 37935
    Prev
    Next
    INDEX
    Explanations

    sync_with_stdio, flush, buffer, Promise

    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
    iggio
    -0.08
    cestor
    -0.07
    å·¥åķĨä¿¡æģ¯
    -0.07
    è¶Ĭéķ¿
    -0.07
    SizePolicy
    -0.07
    .PathVariable
    -0.07
    ãģ«åĪĨ
    -0.07
    æīĭå½ĵ
    -0.07
     nêm
    -0.07
     administrations
    -0.07
    POSITIVE LOGITS
    oyer
    0.07
    .disable
    0.07
    reserve
    0.07
     disable
    0.06
    _suspend
    0.06
    /disable
    0.06
    _FIN
    0.06
    çŃ·
    0.06
    efs
    0.06
    ä¸īéģĵ
    0.06
    Activations Density 0.002%

    No Known Activations