© 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. 25880
    Prev
    Next
    INDEX
    Explanations

    electric fish

    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
    èĢĮå½Ĵ
    -0.09
    æķĻèĤ²åѦéĻ¢
    -0.08
    ç»´å°Ķ
    -0.08
    çݺ
    -0.08
    urian
    -0.07
     XYZ
    -0.07
    å°ĶåŁº
    -0.07
    éĢļ讯åijĺ
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
    ç§ijåѦéĻ¢
    -0.07
    POSITIVE LOGITS
    ç¼Ģ
    0.08
    --
    0.07
    ......
    0.06
    ãĢİ
    0.06
    -(
    0.06
    '-
    0.06
     principally
    0.06
    "-
    0.06
    -/
    0.06
    以èĩ³
    0.06
    Activations Density 7.644%

    No Known Activations