© 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. 40010
    Prev
    Next
    INDEX
    Explanations

    journal, interactions, choice, plane

    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
     uninterrupted
    -0.10
    ä¸įåIJĮçļĦæĺ¯
    -0.08
    -ish
    -0.08
    å¾Ĺä½ı
    -0.08
    assel
    -0.07
     reasonable
    -0.07
     indiv
    -0.07
    ä¸įè¦ģå¿ĺäºĨ
    -0.07
     Kil
    -0.07
     appropriate
    -0.07
    POSITIVE LOGITS
    æĪĸä¸į
    0.11
    æĪĸ缺
    0.11
     altogether
    0.10
    çŃīä¸įèī¯
    0.09
     caused
    0.09
    æĪĸæľª
    0.09
    åİŁåĽłåľ¨äºİ
    0.09
    åıªå¾Ĺ
    0.08
    æŶæľīåıijçĶŁ
    0.08
    èĩ´ä½¿
    0.08
    Activations Density 0.319%

    No Known Activations