© 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. 7927
    Prev
    Next
    INDEX
    Explanations

    earth, feed, it, Arkansas, APIs, health, Strings, telephone, Mercury

    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
    ä¸įçŁ¥æīĢ
    -0.07
    ItemId
    -0.07
    çıĪ
    -0.07
    åıªåī©
    -0.07
    åıªåī©ä¸ĭ
    -0.06
    ä¸Ĭä¸ĭåĬŁå¤«
    -0.06
    æĹłå£°
    -0.06
    ä¸Ĭæ·»
    -0.06
    lier
    -0.06
    毫æĹł
    -0.06
    POSITIVE LOGITS
    SSIP
    0.08
    éĩĩçĶ¨çļĦæĺ¯
    0.08
    æķ´ä½ĵä¸Ĭ
    0.07
    èĻ½æľī
    0.07
    åĬŀ主任
    0.07
    vog
    0.07
     inherently
    0.07
     <!--[
    0.07
    alah
    0.07
    pite
    0.07
    Activations Density 0.101%

    No Known Activations