© 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. 48104
    Prev
    Next
    INDEX
    Explanations

    programming syntax and keywords

    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
    æĢ§åıĬ
    -0.07
    ä¹ĭæĢ¥
    -0.07
    ']].
    -0.07
    à¤ļ
    -0.07
    éĩĩè´Ń代çIJĨæľºæŀĦ
    -0.07
    æĿĢæ°Ķ
    -0.07
    -widgets
    -0.06
    zl
    -0.06
    æµĭè¯ķç»ĵæŀľ
    -0.06
    stadt
    -0.06
    POSITIVE LOGITS
    (...)
    0.09
    ()
    0.08
    ÃŃsmo
    0.08
    `
    0.07
    .xxx
    0.07
    (..
    0.07
    (...
    0.07
    éķ¿é£İ
    0.07
    XXX
    0.07
    åįĥç§ĭ
    0.07
    Activations Density 0.400%

    No Known Activations