© 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. 64908
    Prev
    Next
    INDEX
    Explanations

    after or later

    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
    ation
    -0.10
    ÑİÑĤ
    -0.10
    RARY
    -0.09
    OUNTER
    -0.09
    ×ķ×£
    -0.09
    ible
    -0.08
    à¸ĩาà¸Ļ
    -0.08
    Ñı
    -0.08
    te
    -0.08
    à¹Ģà¸ģà¸Ńรà¹Į
    -0.08
    POSITIVE LOGITS
    éģĹçĹĩ
    0.12
    wards
    0.09
    è§Ĩéķľ
    0.09
    erk
    0.08
    è£Ķ
    0.08
    代çļĦ
    0.08
    iem
    0.08
    羿
    0.08
    æĸĩåĵ²
    0.08
     lintas
    0.07
    Activations Density 0.002%

    No Known Activations