© 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. 28873
    Prev
    Next
    INDEX
    Explanations

    isomers

    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
    hua
    -0.08
    emean
    -0.08
    è¾Ł
    -0.07
    rach
    -0.07
    ursal
    -0.07
    è¡ĢèĤī
    -0.07
    visor
    -0.07
    æĭīåĪ°
    -0.07
    fte
    -0.07
    libc
    -0.07
    POSITIVE LOGITS
     separation
    0.08
    ä»ħéĻIJäºİ
    0.07
    对ä¸įåIJĮ
    0.07
    ä¸įåIJĮç±»åŀĭçļĦ
    0.07
     arises
    0.07
    å¼Ī
    0.07
    主è¦ģåĪĨ为
    0.07
    åı¯åĪĨ为
    0.07
    åŃĺåľ¨äºİ
    0.07
    çļĦé«ĺä½İ
    0.07
    Activations Density 0.004%

    No Known Activations