© 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. 3584
    Prev
    Next
    INDEX
    Explanations

    burst, broadcast, flood, flash

    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
    schau
    -0.09
    umente
    -0.09
    ately
    -0.08
    -même
    -0.08
    schaften
    -0.08
    ếm
    -0.08
    schaft
    -0.08
    ÅĽ
    -0.08
    尼迪
    -0.08
    wai
    -0.07
    POSITIVE LOGITS
    enberg
    0.09
    leigh
    0.08
    ingly
    0.08
    æľŁçļĦ
    0.07
    å¼ıçļĦ
    0.07
    æľŁåĨħ
    0.07
    è¿ĩåIJİ
    0.07
    urs
    0.07
    èĪ¬åľ°
    0.07
    light
    0.07
    Activations Density 0.272%

    No Known Activations