© 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. 18025
    Prev
    Next
    INDEX
    Explanations

    .api, .ui, .jetbrains, dependencies

    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
    uger
    -0.07
    Âł
    -0.07
    inster
    -0.06
    ugh
    -0.06
    /xhtml
    -0.06
    enes
    -0.06
    éģ¥éģ¥
    -0.06
    以ä¸ĭåĩł
    -0.06
    åIJĪ计
    -0.06
    otten
    -0.06
    POSITIVE LOGITS
    nasi
    0.07
     nutris
    0.07
    飽
    0.07
    æ¸¸ä¾ł
    0.07
    OrElse
    0.07
    漫
    0.07
    æ»ĭ
    0.07
     Robbins
    0.07
     polled
    0.07
    âĸ·
    0.07
    Activations Density 0.192%

    No Known Activations