© 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. 18685
    Prev
    Next
    INDEX
    Explanations

    companies and their products

    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
    izio
    -0.08
    esten
    -0.08
    åħĭæĸ¯åĿ¦
    -0.07
    ställ
    -0.07
    濯
    -0.07
    ogne
    -0.07
    梧
    -0.07
    ITLE
    -0.07
    åĴĮ建议
    -0.07
    alking
    -0.07
    POSITIVE LOGITS
    æĸ¹åľĨ
    0.07
    berger
    0.07
    è´§åı·
    0.06
    ä¸įéľĢ
    0.06
     opt
    0.06
    é»ij马
    0.06
     except
    0.06
    llum
    0.06
    final
    0.06
    verte
    0.06
    Activations Density 0.020%

    No Known Activations