© 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. 58437
    Prev
    Next
    INDEX
    Explanations

    wait

    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
     either
    -0.07
    ä¸įåIJĮç¨ĭ度çļĦ
    -0.06
    æĪijæĿ¥è¯´
    -0.06
     hence
    -0.06
    aper
    -0.06
    йдеÑĤ
    -0.06
     blah
    -0.06
    ä¸įåIJĮç¨ĭ度
    -0.06
    çĶŁæķĪä¹ĭæĹ¥èµ·
    -0.06
     ï¼Ī
    -0.06
    POSITIVE LOGITS
     przecież
    0.09
     hiszen
    0.09
    etz
    0.09
    казÑĭваеÑĤÑģÑı
    0.08
    æĴĩ
    0.08
    çĶŁç´ł
    0.08
    iggins
    0.08
    idot
    0.08
    atu
    0.08
    cheon
    0.08
    Activations Density 0.006%

    No Known Activations