© 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. 12612
    Prev
    Next
    INDEX
    Explanations

    steady-state kinetics and rates

    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
    _default
    -0.07
    Default
    -0.06
    ess
    -0.06
    å¤įåİŁ
    -0.06
    blank
    -0.06
     default
    -0.06
    awang
    -0.06
    è°ĥæķ´
    -0.06
    _DEFAULT
    -0.06
    ä¸Ģè¨Ģ
    -0.06
    POSITIVE LOGITS
     births
    0.09
    steady
    0.09
    平衡
    0.08
     bottleneck
    0.08
     steady
    0.08
    Rates
    0.08
    ä¾Ľä¸įåºĶæ±Ĥ
    0.08
    population
    0.08
     balances
    0.08
     kinetics
    0.08
    Activations Density 0.005%

    No Known Activations