© 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. 31874
    Prev
    Next
    INDEX
    Explanations

    `. `

    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
    ä¸Ńå¿ĥåĮ»éĻ¢
    -0.07
     stead
    -0.07
    aspers
    -0.07
     instead
    -0.07
    lius
    -0.07
    ll
    -0.07
    opp
    -0.07
     lÃłnh
    -0.06
    士
    -0.06
    kia
    -0.06
    POSITIVE LOGITS
    åIJİèĢħ
    0.13
     latter
    0.10
    åīįèĢħ
    0.09
     letz
    0.07
    èĢģå°ij
    0.07
     Nhan
    0.07
    被å¥Ĺ
    0.07
    ault
    0.06
    æĥľ
    0.06
    .nb
    0.06
    Activations Density 0.025%

    No Known Activations