© 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. 10029
    Prev
    Next
    INDEX
    Explanations

    describing features or components

    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
    regunta
    -0.07
     paren
    -0.06
    åĭĴæĸ¯
    -0.06
    åĴĮæľīåħ³
    -0.06
    paren
    -0.06
    ij
    -0.06
     Paren
    -0.06
    æīģ
    -0.06
    Paren
    -0.06
    idding
    -0.06
    POSITIVE LOGITS
    åIJİèĢħ
    0.11
    åīįèĢħ
    0.10
    ãģ¨ãĤĤãģ«
    0.10
    è¿Ļ两个
    0.10
    两项
    0.10
     latter
    0.09
     alike
    0.09
    è¿ĻäºĽåĽłç´ł
    0.09
    缺ä¸Ģä¸įåı¯
    0.09
    çļĦä¸ĢåĪĩéĥ½
    0.09
    Activations Density 0.758%

    No Known Activations