© 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. 46948
    Prev
    Next
    INDEX
    Explanations

    file extensions and code names

    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
    лÑĥÑĩ
    -0.08
    viet
    -0.08
    ÑĢÑĥг
    -0.07
    inia
    -0.07
    ueur
    -0.07
    piler
    -0.07
    haft
    -0.07
    edin
    -0.07
    å¹´èĩ³ä»Ĭ
    -0.07
    Unmount
    -0.06
    POSITIVE LOGITS
    缸è¾ħ缸æĪIJ
    0.10
    éºŁ
    0.08
    俱ä¹IJéĥ¨
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    addock
    0.07
    åĬłæĭ¿å¤§
    0.07
    /DTD
    0.07
    quo
    0.07
    æĪĸåħ¶
    0.07
    äºĭåįĬåĬŁåĢį
    0.07
    Activations Density 0.033%

    No Known Activations