© 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. 24884
    Prev
    Next
    INDEX
    Explanations

    sequence prediction

    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
    天äºĨ
    -0.08
    åĪ°ä½İ
    -0.08
    åĪĿåħ¥
    -0.08
    åĪĿ
    -0.08
    ripper
    -0.07
    tabil
    -0.07
    æĹłå°ĺ
    -0.07
    .getOwnPropertyDescriptor
    -0.07
    asti
    -0.07
    ä¸ĢæĿ¡æĿ¡
    -0.07
    POSITIVE LOGITS
    åĽ¾å½¢
    0.09
    èªĮ
    0.08
    è§Ħå¾ĭ
    0.07
     pattern
    0.07
    pattern
    0.07
     morph
    0.07
    åŃĹå½¢
    0.07
    è§Ħå¾ĭçļĦ
    0.07
    çļĦåħĥç´ł
    0.07
    idere
    0.07
    Activations Density 0.001%

    No Known Activations