© 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. 12425
    Prev
    Next
    INDEX
    Explanations

    divergence, diverging, diverged

    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
    iffany
    -0.08
    sworth
    -0.07
    æĿ¥å¾ĹåıĬ
    -0.07
    sv
    -0.07
    spflicht
    -0.07
    urer
    -0.07
    anvas
    -0.07
    lden
    -0.07
     darn
    -0.07
    smith
    -0.07
    POSITIVE LOGITS
    족
    0.11
    /div
    0.10
    ÑĢио
    0.09
    Ùĩ
    0.09
    ible
    0.09
    icult
    0.08
    ed
    0.08
    agai
    0.08
    /null
    0.08
    aison
    0.08
    Activations Density 0.011%

    No Known Activations