© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64042
    Prev
    Next
    INDEX
    Explanations

    arrows or direction symbols

    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
    plements
    -0.08
    ä¹ĥèĩ³
    -0.07
    æ·±åħ¥åľ°
    -0.07
    åºĶå½ĵæĮīçħ§
    -0.07
    à¥įयान
    -0.07
    arez
    -0.07
    æľŁå¾ħæĤ¨çļĦ
    -0.07
    /or
    -0.06
    enden
    -0.06
    ógy
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.08
    åĦ¿çļĦ
    0.08
    ruh
    0.07
    æľ¬æĸĩæĿ¥èĩª
    0.07
    /=
    0.07
    /OR
    0.06
    ï¸İ
    0.06
    åĴļ
    0.06
    клад
    0.06
    ä¸Ĭè¿°ä½ľåĵģ
    0.06
    Activations Density 0.008%

    No Known Activations