© 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. 20990
    Prev
    Next
    INDEX
    Explanations

    mathematical notation 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
    -0.07
    ,
    -0.07
     (
    -0.06
     once
    -0.06
    次çļĦ
    -0.06
     nhau
    -0.06
     marked
    -0.06
    ↵
    -0.06
     ↵
    -0.05
     sigh
    -0.05
    POSITIVE LOGITS
    AttributeName
    0.10
     <![
    0.09
    hut
    0.09
    ä¸Ģ女
    0.09
    æĹ¥èµ·èĩ³
    0.08
    Ø´ÙĬØ©
    0.08
    åįĹèĩ³
    0.08
    TML
    0.08
    isir
    0.08
    aine
    0.08
    Activations Density 0.008%

    No Known Activations