© 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. 63021
    Prev
    Next
    INDEX
    Explanations

    applicable to

    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
    Ĺı
    -0.09
    hetto
    -0.09
    ÅŁik
    -0.09
    缸è¾ħ缸æĪIJ
    -0.08
    zza
    -0.08
    ×ķש
    -0.08
    eger
    -0.08
    èĢĮæĪIJçļĦ
    -0.08
    lamour
    -0.07
    chette
    -0.07
    POSITIVE LOGITS
    licable
    0.08
    ä¹İ
    0.08
    æĥħå½¢
    0.08
    æĥħåĨµ
    0.08
    æĽ´å¹¿
    0.08
    éĢĤçĶ¨
    0.08
    æĥħåĨµçļĦ
    0.08
    æľĢ广
    0.08
    OrElse
    0.07
    è¿Ļç§įæĥħåĨµ
    0.07
    Activations Density 0.021%

    No Known Activations