© 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. 27101
    Prev
    Next
    INDEX
    Explanations

    CurrentPrice coupling

    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
    althy
    -0.08
    åĴĮçī¹çĤ¹
    -0.08
    unning
    -0.07
    åĮĢ
    -0.06
    grade
    -0.06
    éŃģ
    -0.06
    sortBy
    -0.06
    çªģ
    -0.06
    糯
    -0.06
    htmlspecialchars
    -0.06
    POSITIVE LOGITS
    BLOCK
    0.09
    åµĮå¥Ĺ
    0.08
    avian
    0.08
    åĿ
    0.08
    wijk
    0.07
    èİ«åIJį
    0.07
    大人们
    0.07
    建ç«Ļ
    0.07
    aret
    0.07
    äck
    0.07
    Activations Density 0.006%

    No Known Activations