© 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. 32093
    Prev
    Next
    INDEX
    Explanations

    statistical evolution 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
    usse
    -0.07
    æĹłéĺ»
    -0.07
    åĪĩ
    -0.07
    .getvalue
    -0.07
    èĪį
    -0.07
     turnout
    -0.07
     Klos
    -0.06
    è¿Ľåı£
    -0.06
    ç½
    -0.06
     pract
    -0.06
    POSITIVE LOGITS
    积累çļĦ
    0.09
     statistical
    0.09
     evolutionary
    0.08
    ç»Łè®¡
    0.08
     statistics
    0.08
    ç»Łè®¡æķ°æį®
    0.08
    PACE
    0.08
     patterns
    0.08
     characters
    0.07
     accum
    0.07
    Activations Density 0.029%

    No Known Activations