© 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. 50509
    Prev
    Next
    INDEX
    Explanations

    or, rice, white, 5, 0, DC

    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¦ĩ
    -0.07
    omb
    -0.07
    ÅĽl
    -0.07
    _NON
    -0.06
    åıĬæľīåħ³
    -0.06
    æľ¬æĸĩ为
    -0.06
    åIJĦç§įåİŁåĽł
    -0.06
     ÐĶал
    -0.06
    .perm
    -0.06
    =end
    -0.06
    POSITIVE LOGITS
    æĪĸ
    0.13
     or
    0.12
     oder
    0.11
     или
    0.11
     ÛĮا
    0.10
    หรืà¸Ń
    0.10
     hoặc
    0.10
    æĪĸæĺ¯
    0.10
    ãģ¾ãģŁãģ¯
    0.10
     atau
    0.10
    Activations Density 0.064%

    No Known Activations