© 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. 58135
    Prev
    Next
    INDEX
    Explanations

    authoritative and reliable sources

    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
    æľ¬çīĪ
    -0.09
    æĸ°ç¤¾
    -0.09
    åįģä¸ĥç«ł
    -0.08
    irut
    -0.08
    åĽ¾ä¸ŃäºĮç»´çłģ
    -0.08
    è·Łè´´
    -0.08
    vrier
    -0.08
    ikit
    -0.08
     uzu
    -0.07
    OOT
    -0.07
    POSITIVE LOGITS
    æĿĥå¨ģçļĦ
    0.10
    æĿĥå¨ģ
    0.10
     authoritative
    0.10
     reputable
    0.09
    åı¯éĿłçļĦ
    0.09
    æĿĥå¨ģæĢ§
    0.09
     reliable
    0.09
     respected
    0.08
    åı¯éĿł
    0.08
     fiable
    0.08
    Activations Density 0.134%

    No Known Activations