© 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. 40276
    Prev
    Next
    INDEX
    Explanations

    joint probability and models

    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
    apo
    -0.08
    _mapper
    -0.08
    ASI
    -0.07
    éĢĶ
    -0.07
    IAS
    -0.07
    ableView
    -0.07
    .medium
    -0.07
    åħĪåıij
    -0.07
    claimer
    -0.07
    izo
    -0.07
    POSITIVE LOGITS
    æľįä»İ
    0.08
    åľ¨ä¸Ģèµ·
    0.08
    nuts
    0.07
    å¯Ĩä¸įåı¯
    0.07
    åIJĪåĬĽ
    0.07
    鸳
    0.07
    utas
    0.07
     ÑģовмеÑģÑĤ
    0.07
    åIJĪ
    0.07
    åľ¨ä¸Ģèµ·çļĦ
    0.06
    Activations Density 0.003%

    No Known Activations