© 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. 62151
    Prev
    Next
    INDEX
    Explanations

    code and algorithms

    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
    å¦ĩ人
    -0.08
    æĹłå¿Į
    -0.07
    .compiler
    -0.07
    .mutable
    -0.07
    ç»Ļä½łå¸¦æĿ¥
    -0.07
     Hers
    -0.07
    gelt
    -0.07
    acker
    -0.07
    è¿Ľä¸ĢæŃ¥æݨåĬ¨
    -0.06
    å°ģ
    -0.06
    POSITIVE LOGITS
     logic
    0.10
    éĢ»è¾ij
    0.10
    åģ¥
    0.09
     Logic
    0.08
     algorithms
    0.08
     алгоÑĢиÑĤ
    0.08
    ç®Ĺæ³ķ
    0.08
    æµģç¨ĭåĴĮ
    0.08
     lógica
    0.08
     implemented
    0.07
    Activations Density 0.717%

    No Known Activations