© 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. 26787
    Prev
    Next
    INDEX
    Explanations

    but then

    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
    emar
    -0.06
    quel
    -0.06
     definitely
    -0.06
    妥
    -0.06
    kaw
    -0.06
    prud
    -0.06
    áĭ¨
    -0.06
     unequiv
    -0.06
    ³
    -0.06
    è¢
    -0.06
    POSITIVE LOGITS
    åį´ä¸Ģ缴
    0.10
    并ä¸į代表
    0.09
    并ä¸įæĦıåij³çĿĢ
    0.09
    åıĪä¸į
    0.09
    ä¸įåIJĮæŶ
    0.09
    åį´æľī
    0.08
    ä¸į代表
    0.08
    anen
    0.08
    åį´æĺ¯
    0.08
    ANE
    0.08
    Activations Density 0.147%

    No Known Activations