© 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. 29840
    Prev
    Next
    INDEX
    Explanations

    introduction sections

    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
    ervo
    -0.07
    way
    -0.07
    临
    -0.07
    å°½æľī
    -0.06
    çĨŁ
    -0.06
    èĴĻ
    -0.06
    çķ´
    -0.06
    loch
    -0.06
    isoft
    -0.06
    æĺı
    -0.06
    POSITIVE LOGITS
    eliz
    0.08
    ampil
    0.08
    .getRoot
    0.07
     Sections
    0.07
    íļį
    0.07
    arren
    0.07
    appy
    0.07
    rát
    0.07
    áĥĽ
    0.07
    æİ¥ä¸ĭæĿ¥çļĦ
    0.07
    Activations Density 0.066%

    No Known Activations