© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20546
    Prev
    Next
    INDEX
    Explanations

    Width type

    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
    çļĦä¸ĢåĪĩéĥ½
    -0.07
    çļĦåIJĦç§į
    -0.07
    æ¯ıä¸Ģ份
    -0.07
    UDO
    -0.07
    ibly
    -0.07
    çŃł
    -0.06
     hela
    -0.06
     vertrag
    -0.06
    ENV
    -0.06
    éĥ¨çº§
    -0.06
    POSITIVE LOGITS
    åĬ¡
    0.07
    ç»ĵæĿŁåIJİ
    0.07
    çĶļ
    0.07
    å°Ķå¤ļ
    0.07
    ampion
    0.07
    mati
    0.06
    ç¥ĿæĤ¨
    0.06
    çŃĸ
    0.06
    åĭĻ
    0.06
    emper
    0.06
    Activations Density 0.002%

    No Known Activations