© 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. 31265
    Prev
    Next
    INDEX
    Explanations

    every dollar invested

    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
    erk
    -0.08
    dera
    -0.07
    åĪ°åĵª
    -0.07
    ugins
    -0.07
    inti
    -0.06
    ä¹ĭåŃIJ
    -0.06
     tá»ijc
    -0.06
    è°ļ
    -0.06
    åħīæĺ¯
    -0.06
    ä¸īåĽĽ
    -0.06
    POSITIVE LOGITS
    èĻļæĭŁ
    0.08
     hypothetical
    0.08
    éĩıçļĦ
    0.07
    åŁºåľ°å»ºè®¾
    0.07
    æ¯Ķä¾ĭçļĦ
    0.07
    为åįķä½į
    0.07
    หà¸Ļà¹Īวย
    0.07
    æ¯Ķä¾ĭ为
    0.07
    ç«¥åŃIJ
    0.07
    æ²ĻçĽĺ
    0.07
    Activations Density 0.023%

    No Known Activations