© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50061
    Prev
    Next
    INDEX
    Explanations

    generic type parameters

    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
    /etc
    -0.08
    çļĦè¿ĺæľī
    -0.08
    _='
    -0.07
    妬
    -0.07
    noinspection
    -0.07
    âĢ¦the
    -0.07
    ¼
    -0.07
    inken
    -0.07
    nodeName
    -0.07
     ‘’
    -0.07
    POSITIVE LOGITS
     [
    0.06
    èį·
    0.06
     **ãĢIJ
    0.06
     licha
    0.06
    è¾Ľ
    0.06
    çļĦåīį
    0.06
    请è¾ĵåħ¥
    0.06
    .def
    0.06
    heb
    0.06
    á»ģ
    0.06
    Activations Density 0.012%

    No Known Activations