© 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. 23570
    Prev
    Next
    INDEX
    Explanations

    schools, colleges, and performance venues

    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
     desto
    -0.09
    ëĿ¼ëıĦ
    -0.09
    å¦Ĥåľ¨
    -0.08
    .Fore
    -0.08
     nách
    -0.08
    ФС
    -0.08
    ëįĶëĿ¼ëıĦ
    -0.08
    !:
    -0.08
    é½IJæĬĵ
    -0.08
    ìĿ´ëĿ¼ëıĦ
    -0.08
    POSITIVE LOGITS
    åIJĮæŶè¿ĺ
    0.06
    engeb
    0.06
    æĪĸèĢħæĺ¯
    0.06
    eng
    0.06
     (),
    0.06
    alse
    0.06
     (
    0.06
    å¾Ĺå¿ĥ
    0.06
    åĪģ
    0.06
    1
    0.06
    Activations Density 2.003%

    No Known Activations