© 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. 32657
    Prev
    Next
    INDEX
    Explanations

    numbers 0-256

    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
    麾
    -0.07
    禦
    -0.07
    ches
    -0.06
    èĸĦ
    -0.06
    ellen
    -0.06
    пе
    -0.06
    оз
    -0.06
    è·»
    -0.06
    æĿ¥ä¸´
    -0.06
    lili
    -0.06
    POSITIVE LOGITS
    esso
    0.08
    ï¸ı
    0.08
    steen
    0.08
    quio
    0.08
    sworth
    0.08
    gba
    0.07
    imax
    0.07
    �
    0.07
    0.07
    ertia
    0.07
    Activations Density 0.096%

    No Known Activations