© 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. 13961
    Prev
    Next
    INDEX
    Explanations

    denote or let statements

    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
    iom
    -0.08
    istrar
    -0.07
    çļĦç¡®æĺ¯
    -0.07
    erso
    -0.07
    çļĦåı¦ä¸Ģ
    -0.07
    uable
    -0.07
     comparatively
    -0.07
    ubbo
    -0.07
    .baidu
    -0.07
    使ä¹ĭ
    -0.07
    POSITIVE LOGITS
     denote
    0.09
     denotes
    0.08
    空éĻį
    0.07
    çı
    0.07
    [Math
    0.07
    å¨Ł
    0.07
     shorthand
    0.06
    çĦķ
    0.06
    _LOAD
    0.06
    çĶľ
    0.06
    Activations Density 0.016%

    No Known Activations