© 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. 41575
    Prev
    Next
    INDEX
    Explanations

    momentum, velocity, energy, physics

    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
    ordinal
    -0.07
    anzi
    -0.07
    æĢģ度åĴĮ
    -0.06
    宦
    -0.06
    çĪ¬åĪ°
    -0.06
     vòi
    -0.06
    pig
    -0.06
    fty
    -0.06
    uble
    -0.06
    èĥ¡åŃIJ
    -0.06
    POSITIVE LOGITS
    çŁ¢
    0.09
    omentum
    0.08
    riad
    0.07
    ëłĪìĬ¤
    0.07
    çŁ¢éĩı
    0.07
    ×ķ×IJ
    0.07
     дÑĢе
    0.07
    esas
    0.07
    utherford
    0.07
     kin
    0.07
    Activations Density 0.003%

    No Known Activations