© 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. 15406
    Prev
    Next
    INDEX
    Explanations

    limited perspective

    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
    åĽłä¸ºè¿Ļ
    -0.09
    ereg
    -0.09
    aire
    -0.08
    tory
    -0.08
    coes
    -0.07
     EVER
    -0.07
    åĽłä¸ºè¿ĻäºĽ
    -0.07
    resco
    -0.07
    bbbb
    -0.07
    为好
    -0.07
    POSITIVE LOGITS
    æ½ľåľ¨
    0.08
     поÑĤенÑĨи
    0.08
    igia
    0.07
    æ½ľåľ¨çļĦ
    0.07
     potential
    0.07
     potentially
    0.07
     trivial
    0.07
    æĽ´éĩįè¦ģçļĦæĺ¯
    0.06
     поÑĤен
    0.06
    èĩ
    0.06
    Activations Density 0.101%

    No Known Activations