© 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. 2705
    Prev
    Next
    INDEX
    Explanations

    investigation was

    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
    ç¾İ好çļĦæľªæĿ¥
    -0.07
    áĢ²áĢ·
    -0.06
    çľģæĶ¿åºľ
    -0.06
     Hung
    -0.06
    —but
    -0.06
    à±įయా
    -0.06
    æ°¸è¿ľä¸įä¼ļ
    -0.06
    å¦ĤçĥŁ
    -0.06
    à¸ķัà¹īà¸ĩ
    -0.06
    çªģåĩ»éĺŁ
    -0.06
    POSITIVE LOGITS
    èĩªä¸ª
    0.10
    害
    0.08
    mvc
    0.08
    antemente
    0.08
    ubes
    0.08
    udies
    0.08
    èĮĥçķ´
    0.07
    åĢĺèĭ¥
    0.07
    igans
    0.07
    ç½¢äºĨ
    0.07
    Activations Density 0.566%

    No Known Activations