© 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. 30633
    Prev
    Next
    INDEX
    Explanations

    convert

    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
    太éĥİ
    -0.08
    /utility
    -0.08
    /gpl
    -0.07
    bedo
    -0.07
    (red
    -0.07
    æĪijæĬĬ
    -0.07
    aler
    -0.07
    æĬĬ
    -0.06
    undi
    -0.06
    æĬĬ好
    -0.06
    POSITIVE LOGITS
    /from
    0.10
    å®ŀéĻħçļĦ
    0.08
    æŶä¼ļ
    0.07
    æŶåı¯
    0.07
    åı¦å¤ĸä¸Ģç§į
    0.07
    åIJİåı¯
    0.07
     actual
    0.07
    æĽ´èĥ½
    0.07
    erva
    0.07
     usable
    0.07
    Activations Density 0.037%

    No Known Activations