© 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. 60200
    Prev
    Next
    INDEX
    Explanations

    FIG

    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
     Фло
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.06
    ç®ĹäºĨ
    -0.06
    ç²īåĪ·
    -0.06
    ä¸įä¹±
    -0.06
     flo
    -0.06
     certeza
    -0.06
    sau
    -0.06
    常åIJĥ
    -0.06
    溢
    -0.06
    POSITIVE LOGITS
    æīĢ示
    0.10
    orney
    0.09
    гоÑĢа
    0.08
    åĽ¾çŃī
    0.08
    alet
    0.08
    åĽ¾çº¸
    0.08
     diagram
    0.08
     diagrams
    0.08
    ä¸ĵ家ä»ĭç»į
    0.07
     deten
    0.07
    Activations Density 0.037%

    No Known Activations