© 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. 60992
    Prev
    Next
    INDEX
    Explanations

    diagrams and lists

    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
    åīį款
    -0.07
    casting
    -0.07
    kans
    -0.06
    æĪIJç«ł
    -0.06
    onato
    -0.06
    amani
    -0.06
    åijĬ
    -0.06
    åĴ¯
    -0.06
    overs
    -0.06
     zlib
    -0.06
    POSITIVE LOGITS
    åĽ¾ç¤º
    0.25
    å¦ĤåĽ¾æīĢ示
    0.24
    示æĦıåĽ¾
    0.23
    åĽ¾ä¸Ń
    0.23
     diagram
    0.23
    å¦ĤåĽ¾
    0.22
    ä¸ĭåĽ¾
    0.22
    å¦Ĥä¸ĭåĽ¾æīĢ示
    0.22
    å¦Ĥä¸ĭåĽ¾
    0.22
    åĽ¾ä¸ŃçļĦ
    0.21
    Activations Density 0.733%

    No Known Activations