© 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. 29993
    Prev
    Next
    INDEX
    Explanations

    table structures

    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
    yen
    -0.06
    éĻIJäºİ
    -0.06
    ney
    -0.06
    chel
    -0.06
    ilton
    -0.06
    ¸
    -0.06
    ÙĪارÙĩ
    -0.06
    mes
    -0.06
    cheon
    -0.06
    uls
    -0.06
    POSITIVE LOGITS
    lise
    0.08
    locks
    0.08
    çļĻ
    0.07
    |"
    0.07
    åİ»ä½ķ
    0.07
    ä¼¼æĺ¯
    0.07
    spath
    0.07
    ×ķ×¢
    0.07
    stro
    0.07
    .outer
    0.07
    Activations Density 0.074%

    No Known Activations