© 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. 13355
    Prev
    Next
    INDEX
    Explanations

    closing brackets, punctuation

    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
    头
    -0.07
    Âł
    -0.07
    eka
    -0.07
    大èĩ´
    -0.06
    odb
    -0.06
    hia
    -0.06
    omain
    -0.06
    è¿ĺæľīä»Ģä¹Ī
    -0.06
    æµ
    -0.06
     bound
    -0.06
    POSITIVE LOGITS
    =cut
    0.08
    éĺħ读åħ¨æĸĩ
    0.08
    罪éŃģ
    0.07
    å·¥æĪ¿
    0.07
    ä¹Łæĺ¯åįģåĪĨ
    0.07
    oksi
    0.07
    ç¼ĸè¾ijæݨèįIJ
    0.07
    æŁ¥çľĭçŃĶæ¡Ī
    0.07
    çŃĶ主
    0.07
    æ¯ĶåĪ«äºº
    0.07
    Activations Density 0.001%

    No Known Activations