© 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. 34184
    Prev
    Next
    INDEX
    Explanations

    court of appeals

    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
      ↵↵
    -0.07
    ese
    -0.07
    ม
    -0.07
    éľĦ
    -0.07
      ↵    ↵
    -0.06
    èį·
    -0.06
    ↵↵
    -0.06
    ype
    -0.06
    ####
    -0.06
    çļĦä¸įåIJĮ
    -0.06
    POSITIVE LOGITS
    <|repo_name|>
    0.07
    该楼å±Ĥçĸijä¼¼è¿Ŀè§Ħå·²è¢«ç³»ç»ŁæĬĺåıł
    0.07
    tools
    0.07
    ouncy
    0.07
    itzer
    0.07
    orghini
    0.07
    ä¸Ĭä½į
    0.07
     chá»ijn
    0.07
    ì°°
    0.07
    weigh
    0.07
    Activations Density 0.669%

    No Known Activations