© 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. 30631
    Prev
    Next
    INDEX
    Explanations

    mathematical notation or code snippets

    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
    tev
    -0.08
    urch
    -0.08
    intang
    -0.07
    ðŁĺī
    -0.07
    Å¡anu
    -0.07
     thereof
    -0.07
    ukul
    -0.07
    å¦Ĥä¸ĭ
    -0.07
    æľ¬æĸĩæĿ¥èĩª
    -0.07
     Parch
    -0.07
    POSITIVE LOGITS
    etheless
    0.08
    ÙĢÙĢÙĢÙĢÙĢÙĢÙĢÙĢ
    0.08
    0.08
     ::=
    0.08
     <![
    0.07
    0.07
    0.07
    åīį款
    0.07
    æľ¬æ¥¼
    0.07
     nemlig
    0.07
    Activations Density 0.027%

    No Known Activations