© 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. 43278
    Prev
    Next
    INDEX
    Explanations

    group velocity dispersion

    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
    anty
    -0.08
    entries
    -0.08
    vida
    -0.08
    istre
    -0.07
    ÐľÐļ
    -0.07
    tsky
    -0.07
    aç
    -0.07
    æĮijæĪĺæĢ§
    -0.07
    éĩı身
    -0.07
    ä¸īçĻ¾
    -0.07
    POSITIVE LOGITS
     tangent
    0.07
     Navarra
    0.07
     velocity
    0.07
    庸
    0.07
    hunt
    0.07
    _velocity
    0.07
    å¼¹
    0.07
     velocities
    0.07
    hack
    0.07
     emergence
    0.07
    Activations Density 0.002%

    No Known Activations