© 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. 2208
    Prev
    Next
    INDEX
    Explanations

    grams in kilograms

    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
    elf
    -0.07
    .URL
    -0.06
    åįĬçĤ¹
    -0.06
    rows
    -0.06
    ä¸īçĶŁ
    -0.06
    åĻ¨æĿIJ
    -0.06
    apur
    -0.06
    èģª
    -0.05
    IAL
    -0.05
    å¤ĸ表
    -0.05
    POSITIVE LOGITS
    ienza
    0.08
    ngen
    0.08
    æļĤè¡Į
    0.08
    OKEN
    0.08
    æĻ´ç©º
    0.07
    velle
    0.07
    roż
    0.07
    edos
    0.07
    odox
    0.07
    tiers
    0.07
    Activations Density 0.001%

    No Known Activations