© 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. 43908
    Prev
    Next
    INDEX
    Explanations

    such that

    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
    ½
    -0.07
    æ·«
    -0.07
    mr
    -0.06
    ç®Ĺä»Ģä¹Ī
    -0.06
    ä½ľä¸ºä¸Ģç§į
    -0.06
    å¼Ģå§ĭåīį
    -0.06
    æīĢ以ä»ĸ们
    -0.06
    çļĦåįķ
    -0.06
    æľīä¸Ģä½į
    -0.06
    åIJ¸å¼ķäºĨä¼Ĺå¤ļ
    -0.06
    POSITIVE LOGITS
     whose
    0.11
    使å¾Ĺ
    0.10
    whose
    0.09
    使èĩªå·±çļĦ
    0.08
     ÑĩÑĤобÑĭ
    0.08
     that
    0.08
     daÃŁ
    0.08
     Äijá»ĥ
    0.07
    è¯ģæį®è¯ģæĺİ
    0.07
    æĢ»ç®¡
    0.07
    Activations Density 0.014%

    No Known Activations