© 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. 31074
    Prev
    Next
    INDEX
    Explanations

    program termination commands

    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
    ä¸ĭåIJĮ
    -0.09
    adero
    -0.07
    ...',
    -0.07
    èĶĹ
    -0.07
    aur
    -0.07
    uset
    -0.07
    croft
    -0.07
    ader
    -0.07
    èİħ
    -0.07
    åIJįä¹ī
    -0.07
    POSITIVE LOGITS
    æ·»
    0.08
    гÑĢе
    0.07
    mana
    0.07
    AGR
    0.06
    afil
    0.06
    xaa
    0.06
    emu
    0.06
    QueryBuilder
    0.06
    roj
    0.06
    yai
    0.06
    Activations Density 0.001%

    No Known Activations