© 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. 7614
    Prev
    Next
    INDEX
    Explanations

    not enough, not working, unacceptable

    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
    èĢĮä¸įæĺ¯
    -0.09
    ä¸įæĺĵ
    -0.08
     rather
    -0.08
    ä¸įä¸Ģå®ļ
    -0.08
    èĢĮéĿŀ
    -0.07
    åIJĦç§į
    -0.07
    rather
    -0.07
    ä¸įæĸŃåĬªåĬĽ
    -0.07
    ä¸įä¹±
    -0.07
    ä¸į容æĺĵ
    -0.07
    POSITIVE LOGITS
     sequer
    0.13
     anymore
    0.12
    æľīä»»ä½ķ
    0.11
    ä»»ä½ķå½¢å¼ıçļĦ
    0.10
    æĽ´ä¸įèĥ½
    0.10
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.10
    ä»»ä½ķä¸Ģ个
    0.10
    æıIJä¾Ľä»»ä½ķ
    0.10
    éĻ¤éĿŀ
    0.09
     siquiera
    0.09
    Activations Density 0.081%

    No Known Activations