© 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. 26332
    Prev
    Next
    INDEX
    Explanations

    size, class, or coordinates followed by colon/equals

    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
     Baz
    -0.07
    å´©
    -0.06
    æĪĸæľª
    -0.06
    ::-
    -0.06
    æĪĸä¸İ
    -0.06
    æĹ¢
    -0.06
     Too
    -0.06
    æĿ¥åİĨ
    -0.05
     (
    -0.05
     or
    -0.05
    POSITIVE LOGITS
    ecte
    0.08
    richt
    0.08
    pedo
    0.08
    ecker
    0.08
    DAH
    0.08
    rapper
    0.08
    LEM
    0.08
    å¾ĹçĽĬ
    0.08
    rasil
    0.08
    ä¹ħèĢĮ
    0.08
    Activations Density 0.345%

    No Known Activations