© 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. 49025
    Prev
    Next
    INDEX
    Explanations

    mystery series

    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
    æ±Łè·¯
    -0.08
    tock
    -0.07
    -plugins
    -0.07
    ilat
    -0.07
    åįļä¼ļ
    -0.07
    OnError
    -0.07
    ori
    -0.07
    ogu
    -0.07
    ç¹
    -0.06
     appunto
    -0.06
    POSITIVE LOGITS
    å°½åľ¨
    0.09
    交æµģ群
    0.07
    çļĦä¸Ģå¼ł
    0.07
    Ñħай
    0.06
    åĬłæĭ¿å¤§
    0.06
    ина
    0.06
    гда
    0.06
    sze
    0.06
    asten
    0.06
    ÑĤÑĢ
    0.06
    Activations Density 0.677%

    No Known Activations