© 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. 65498
    Prev
    Next
    INDEX
    Explanations

    bound the

    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
    stands
    -0.07
    pond
    -0.07
    空çļĦ
    -0.07
    ield
    -0.07
    .arr
    -0.07
    满身
    -0.06
    å¹¶è¿Ľ
    -0.06
    ÑĩеÑĢед
    -0.06
     Chart
    -0.06
    erti
    -0.06
    POSITIVE LOGITS
    è¦ĭç©į
    0.07
    ateg
    0.07
    _MPI
    0.07
    strap
    0.07
    æľªçĦ¶
    0.07
     giỼi
    0.07
    èĥŃ
    0.07
    éĻIJ度çļĦ
    0.07
    ä¸į严
    0.07
    eware
    0.07
    Activations Density 0.009%

    No Known Activations