© 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. 41685
    Prev
    Next
    INDEX
    Explanations

    time constants, delay, decay

    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
    İ
    -0.08
    åħ«éĥ¨
    -0.07
    juk
    -0.07
    æĹłæ±¡æŁĵ
    -0.07
    antium
    -0.07
    è¾Ľèĭ¦çļĦ
    -0.07
    zyw
    -0.07
    Ñģловно
    -0.07
     кÑĥÑģ
    -0.07
    /raw
    -0.07
    POSITIVE LOGITS
     delay
    0.09
    Delay
    0.09
     capacit
    0.09
     Delay
    0.09
    ponential
    0.08
    delay
    0.08
     decay
    0.08
     delays
    0.08
     resistor
    0.08
    DELAY
    0.08
    Activations Density 0.003%

    No Known Activations