© 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. 33892
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
     respectively
    -0.06
    tron
    -0.06
     Enhanced
    -0.06
    bere
    -0.06
    ragon
    -0.06
    å±ij
    -0.06
    dio
    -0.06
    assistant
    -0.06
    罪æģ¶
    -0.06
    ->
    -0.06
    POSITIVE LOGITS
    åķ¸
    0.08
    æļ
    0.08
    àºŃàºĩ
    0.07
    ä¸įåı¯æĢķ
    0.07
    ä¹ĭåĴĮ
    0.07
    itoris
    0.07
    ionali
    0.07
    ä¸Ģç¬ij
    0.07
    gue
    0.07
    ij
    0.07
    Activations Density 0.008%

    No Known Activations