© 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. 41974
    Prev
    Next
    INDEX
    Explanations

    latex integrals

    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
    ÏĢη
    -0.07
    ä»ĬåIJİçļĦ
    -0.06
    kea
    -0.06
    sp
    -0.06
    thr
    -0.06
    zá
    -0.06
    inke
    -0.06
    æīī
    -0.06
    ss
    -0.06
    eed
    -0.06
    POSITIVE LOGITS
    delen
    0.08
    赤
    0.08
    elog
    0.07
    RTOS
    0.07
    lado
    0.07
    -Feb
    0.07
    ertext
    0.07
    -bars
    0.07
    ugins
    0.07
    glieder
    0.07
    Activations Density 0.004%

    No Known Activations