© 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. 41012
    Prev
    Next
    INDEX
    Explanations

    change and unexpectedness

    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
    ë°±
    -0.07
    ä»ħä»£è¡¨ä½ľèĢħæľ¬äºº
    -0.07
    åĪ¶åº¦å»ºè®¾
    -0.07
    èī¯
    -0.07
    ä¸įæľ½
    -0.07
    訣
    -0.07
    bau
    -0.07
    onet
    -0.07
     disrupted
    -0.06
    apur
    -0.06
    POSITIVE LOGITS
    ä¸İåİŁ
    0.11
    è¶ħåĩº
    0.11
    åıĺæĽ´åIJİ
    0.10
     unfore
    0.10
    åıĺæĽ´
    0.09
     surprises
    0.09
     unexpected
    0.09
    追åĬł
    0.09
    æĵħèĩª
    0.08
    ä¸ĢæĪIJ
    0.08
    Activations Density 0.066%

    No Known Activations