© 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. 31127
    Prev
    Next
    INDEX
    Explanations

    numeric sequence suffixes, code footnotes, or copyright notices

    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
    enchmark
    -0.08
    rene
    -0.08
    ovich
    -0.08
    å¦ĤçĥŁ
    -0.08
     specialist
    -0.07
    UnderTest
    -0.07
    æłijä¸ĬçļĦ
    -0.07
    unkte
    -0.07
     yah
    -0.07
    orn
    -0.07
    POSITIVE LOGITS
    ajari
    0.07
    .Magic
    0.07
    èĥ´
    0.07
    æĪij们æľī
    0.07
    è¿Ľè¡ĮåŃ¦ä¹ł
    0.07
    大éĥ¨
    0.06
    è¿Ľè¡Įå®£ä¼ł
    0.06
    åľ¨èº«
    0.06
    è¿Ľè¡Į管çIJĨ
    0.06
    建åĨĽ
    0.06
    Activations Density 0.001%

    No Known Activations