© 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. 64828
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

    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
     following
    -0.07
    \.
    -0.06
    à¹Ģà¸Ĺà¹Īา
    -0.06
    _CA
    -0.06
     Martin
    -0.06
    valt
    -0.06
    acre
    -0.06
    —a
    -0.06
    åıªæıIJä¾Ľ
    -0.06
     CA
    -0.05
    POSITIVE LOGITS
    assed
    0.08
    ectividad
    0.08
    ardon
    0.08
     sỹ
    0.07
    _characters
    0.07
    peon
    0.07
    èįīæľ¨
    0.07
    HERE
    0.07
    ä¸Ģåı¶
    0.07
    èĸ°
    0.07
    Activations Density 0.007%

    No Known Activations