© 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. 10265
    Prev
    Next
    INDEX
    Explanations

    pulse wave, pulse discharge, pulse width, pulse pressure

    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
    shire
    -0.10
    ctions
    -0.09
    istrator
    -0.09
    ields
    -0.08
    lander
    -0.08
    ardt
    -0.08
    æĹłèĻij
    -0.08
    ths
    -0.07
    utsch
    -0.07
    annis
    -0.07
    POSITIVE LOGITS
    sticks
    0.08
    mehr
    0.08
    ÑĤоÑĢа
    0.08
    stick
    0.08
    Õ²
    0.07
    ¢
    0.07
    less
    0.07
    ewnÄħ
    0.07
    ÑģледÑĥ
    0.07
    ä¸įä¼ij
    0.07
    Activations Density 0.022%

    No Known Activations