© 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. 16649
    Prev
    Next
    INDEX
    Explanations

    \frac{d}{

    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
     Baj
    -0.07
    ç¡ħè°·
    -0.06
     windy
    -0.06
    @m
    -0.06
    åIJĮ人
    -0.06
     mall
    -0.06
     vie
    -0.06
    /main
    -0.06
     divers
    -0.06
     Sunshine
    -0.06
    POSITIVE LOGITS
    alyzer
    0.07
    ä¸Ģè§Ī表
    0.07
    ifferential
    0.07
    å¢ŀ
    0.07
    icut
    0.07
    èį·
    0.07
    iali
    0.07
    istique
    0.07
     <![
    0.07
    atts
    0.07
    Activations Density 0.009%

    No Known Activations