© 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. 28891
    Prev
    Next
    INDEX
    Explanations

    rate, unit, period, concentration, number, component

    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
    使ä»ĸ们
    -0.08
     Wart
    -0.08
    红楼
    -0.08
    otto
    -0.08
     jelent
    -0.08
    izzi
    -0.08
    OTTO
    -0.07
     nub
    -0.07
    digit
    -0.07
    åİ»éĿ¢å¯¹
    -0.07
    POSITIVE LOGITS
    æĹħ
    0.07
    unit
    0.07
    åįķä½į
    0.07
    ä¸Īéĩı
    0.06
     unit
    0.06
    /vnd
    0.06
     per
    0.06
    çŃīåįķä½į
    0.06
    resa
    0.06
    âĢ¦
    0.06
    Activations Density 0.002%

    No Known Activations