© 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. 58362
    Prev
    Next
    INDEX
    Explanations

    expectation or surprise

    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
    æīĢå±ŀè¡Įä¸ļ
    -0.07
    _ATOM
    -0.07
    大计
    -0.07
    escu
    -0.07
    æķĻäºİ
    -0.07
    å¿ħèĥľ
    -0.07
     اÙĦÙĥب
    -0.07
    _STRIP
    -0.06
    æĢĿæĥ³åĴĮè¡ĮåĬ¨
    -0.06
    accia
    -0.06
    POSITIVE LOGITS
    since
    0.08
    åĽłä¸ºåıªæľī
    0.08
     since
    0.08
    æ¯ķç«Ł
    0.07
    åĺĽ
    0.07
    åĽłä¸ºåľ¨
    0.07
    راÙħ
    0.07
    æĹ¢çĦ¶
    0.07
    åĽłä¸º
    0.07
     configurable
    0.06
    Activations Density 0.067%

    No Known Activations