© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61898
    Prev
    Next
    INDEX
    Explanations

    code elements and numbers

    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
    åı®
    -0.07
    çļĦåľºæīĢ
    -0.06
     Uncle
    -0.06
    åĪĨåĪ«åľ¨
    -0.06
     Zone
    -0.06
    çĻ»ä¸Ĭ
    -0.06
    forth
    -0.06
    Sa
    -0.06
    ç¿»å¼Ģ
    -0.06
    ol
    -0.06
    POSITIVE LOGITS
    ầm
    0.08
    æĸ°åĬłåĿ¡
    0.08
    æĹłæĦ§
    0.08
    ilag
    0.07
    uide
    0.07
    INGK
    0.07
    gfx
    0.07
    ÙĪزÙĩ
    0.07
    天å¸Ī
    0.07
    .getRow
    0.07
    Activations Density 0.002%

    No Known Activations