© 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. 1464
    Prev
    Next
    INDEX
    Explanations

    words after periods

    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
    icante
    -0.07
    ì²Ļ
    -0.07
    apak
    -0.07
    lbrace
    -0.07
    <|im_start|>
    -0.07
    ÏĥÏĩ
    -0.06
    clid
    -0.06
    UGHT
    -0.06
    æĪİ
    -0.06
    UPLE
    -0.06
    POSITIVE LOGITS
    è¿ĺæľīä¸Ģç§į
    0.08
    è¿ĺåı¯
    0.08
    åı¦å¤ĸè¿ĺæľī
    0.07
    è¿ĺæľī个
    0.07
    è¿ĺæľīä¸Ģ个
    0.07
    ¡´
    0.07
    碰åĪ°
    0.07
     übrigens
    0.07
    è¿ĺæľīä¸ĢçĤ¹
    0.07
    åı¦å¤ĸ
    0.07
    Activations Density 0.455%

    No Known Activations