© 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. 57112
    Prev
    Next
    INDEX
    Explanations

    code following filepaths or documents

    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¸įæ¸ħæ¥ļ
    -0.07
     Decompiled
    -0.07
    à¹īà¸ĩ
    -0.06
    azor
    -0.06
    /animate
    -0.06
    ÑĤвоÑĢÑı
    -0.06
    çļĦå¤§çľ¼çĿĽ
    -0.06
    ulare
    -0.06
    åĴĮå¤ĸ
    -0.06
    åĬ¨èĦī硬åĮĸ
    -0.06
    POSITIVE LOGITS
    äºĭåįĬåĬŁåĢį
    0.08
    ij
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    ongan
    0.07
    åĭĩå¾Ģ缴åīį
    0.07
    ilton
    0.07
    olina
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    tale
    0.07
    Activations Density 0.437%

    No Known Activations