© 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. 3059
    Prev
    Next
    INDEX
    Explanations

    friction and related concepts

    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
    å¸ĮæľĽå¯¹æĤ¨
    -0.08
    ç»İ
    -0.08
    edly
    -0.08
     fleste
    -0.08
    ×ķ×¢
    -0.08
    gaard
    -0.08
    OrUpdate
    -0.07
    OrDefault
    -0.07
    ibia
    -0.07
    hood
    -0.07
    POSITIVE LOGITS
    Ùĩ
    0.09
    less
    0.09
    alha
    0.09
    al
    0.08
    an
    0.08
    er
    0.08
    isht
    0.08
    kle
    0.07
    aná
    0.07
    stone
    0.07
    Activations Density 0.009%

    No Known Activations