© 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. 64788
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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
    ä¹İåħ¶
    -0.07
    æľĢå·®
    -0.07
    ä¸Ģ个éĹ®é¢ĺ
    -0.07
    asInstanceOf
    -0.07
    èѦåĬĽ
    -0.07
    toHaveLength
    -0.06
    ç²¾ç¥ŀä¸Ĭ
    -0.06
    .raises
    -0.06
    ä¸įç¦ģ
    -0.06
    ä¸įæĶ¹
    -0.06
    POSITIVE LOGITS
    åĨ¤
    0.07
    ç«ĭãģ¦
    0.07
    èIJĮèIJĮ
    0.07
     lẽ
    0.07
    tage
    0.06
    ä¸ĢæĹ¦è¢«
    0.06
    ÑĢÑĸ
    0.06
    leted
    0.06
    angk
    0.06
    rire
    0.06
    Activations Density 0.024%

    No Known Activations