© 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. 60552
    Prev
    Next
    INDEX
    Explanations

    header file format

    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
    æĽĻ
    -0.07
    ombok
    -0.06
    plement
    -0.06
    elit
    -0.06
    åłĤçļĩ
    -0.06
    ศึà¸ģษา
    -0.06
    rä
    -0.06
    aner
    -0.06
    веÑģÑĤ
    -0.06
    à§ĩলা
    -0.06
    POSITIVE LOGITS
    Ø©
    0.10
    itecture
    0.09
    ÏĤ
    0.08
    bara
    0.08
    ness
    0.08
    illeurs
    0.08
    edly
    0.08
    yll
    0.07
    å©Ĩ
    0.07
    новÑĮ
    0.07
    Activations Density 0.054%

    No Known Activations