© 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. 1691
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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
    ivet
    -0.07
    ola
    -0.07
    llu
    -0.07
    认è¯ĨçļĦ
    -0.06
    óny
    -0.06
    emo
    -0.06
    istol
    -0.06
    icone
    -0.06
    elf
    -0.06
    icon
    -0.06
    POSITIVE LOGITS
    ä¸įæĢĿ
    0.08
    åľ¨çľģ
    0.07
    FromClass
    0.07
    ignum
    0.07
    lott
    0.07
    distributed
    0.07
    ARGER
    0.07
    OfType
    0.07
    ële
    0.07
    åľ¨æ·±åľ³
    0.07
    Activations Density 0.001%

    No Known Activations