© 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. 31374
    Prev
    Next
    INDEX
    Explanations

    foreign language characters or symbols

    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
    uÅĤ
    -0.08
    ergestellt
    -0.07
     nom
    -0.07
    ä½łæķ¢
    -0.06
     doc
    -0.06
    ophone
    -0.06
    åĢĴåľ¨åľ°
    -0.06
    ä¸ĢçĤ¹åĦ¿
    -0.06
    åīįè¿°
    -0.06
     Sujet
    -0.06
    POSITIVE LOGITS
     ****************************************************************
    0.07
    itto
    0.07
    itten
    0.07
    %=
    0.07
    egi
    0.07
    irsch
    0.06
    icidad
    0.06
    ç»Ħè¯į
    0.06
    ç½·
    0.06
    (#)
    0.06
    Activations Density 0.022%

    No Known Activations