© 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. 25200
    Prev
    Next
    INDEX
    Explanations

    Subject: fix / tweak / patch

    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
    ç«Ńè¯ļ
    -0.09
    æĹłå¿§æĹłèĻij
    -0.08
    stroy
    -0.07
    ERSHEY
    -0.07
     events
    -0.07
    irem
    -0.07
    ëł´
    -0.07
    æī¿åĬŀ
    -0.07
    è¦ģçľĭ
    -0.07
    æ¯ıéļĶ
    -0.07
    POSITIVE LOGITS
     Fixes
    0.07
    åīįç½®
    0.07
    å°ıå¹ħ
    0.07
    éĩľ
    0.07
     resh
    0.06
    æīĢåģļçļĦ
    0.06
    ä¿®å¤į
    0.06
     tweak
    0.06
    htag
    0.06
     cherry
    0.06
    Activations Density 0.056%

    No Known Activations