© 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. 51358
    Prev
    Next
    INDEX
    Explanations

    json keys

    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
    ylist
    -0.07
    æĺ¯ä¸įä¸Ģæł·çļĦ
    -0.07
    两ä¸ī
    -0.06
    oni
    -0.06
    æĨ¬
    -0.06
    olos
    -0.06
    æļĩ
    -0.06
    èĸª
    -0.06
    sty
    -0.06
    ordan
    -0.06
    POSITIVE LOGITS
    人
    0.07
    änen
    0.07
    ãĥŀãĥĪ
    0.07
    μÏİν
    0.07
    åIJįçĤº
    0.07
    _named
    0.07
    NAME
    0.07
    ÑĢÑĥÑĤ
    0.07
    åIJį
    0.07
    ectes
    0.07
    Activations Density 0.002%

    No Known Activations