© 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. 60331
    Prev
    Next
    INDEX
    Explanations

    Client Relations Blog

    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
    ollah
    -0.08
    -China
    -0.08
    æķĻåŃ¦æ°´å¹³
    -0.07
    åĵģè´¨çļĦ
    -0.07
    alj
    -0.07
    表示èĩªå·±
    -0.07
    èĦıåĻ¨
    -0.07
    çļĦ好å¥ĩ
    -0.07
    irme
    -0.07
    rapped
    -0.07
    POSITIVE LOGITS
    ä¸ĢèĤ¡
    0.07
    並ãģ³
    0.07
    åĽłèĢĮ
    0.07
    身份è¯ģ
    0.06
    uter
    0.06
    leccion
    0.06
    ooks
    0.06
    utex
    0.06
    ubar
    0.06
    å½ĵæŶ
    0.06
    Activations Density 0.050%

    No Known Activations