© 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. 61195
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    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
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    ;
    -0.06
    ï¼Į
    -0.06
    åľ¨è¿Ľè¡Į
    -0.06
     (
    -0.06
    ;",
    -0.06
    åħ¶
    -0.06
    ï¼Ľ
    -0.06
    æĭ¥æľīçĿĢ
    -0.05
    æį¢åı¥è¯Ŀ说
    -0.05
    POSITIVE LOGITS
    ä¸ĭåIJĮ
    0.10
    langen
    0.08
    ntag
    0.08
    ä¹ŁæĽ´åĬł
    0.08
    vida
    0.08
    ä¹ŁæĽ´
    0.08
    ÑĢики
    0.08
    家æĿij
    0.08
    puis
    0.08
    ä¹ħä¹ĭ
    0.08
    Activations Density 0.036%

    No Known Activations