© 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. 16598
    Prev
    Next
    INDEX
    Explanations

    proof and demonstration

    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
    \/\/
    -0.08
    ä½İçĿĢ头
    -0.08
     desto
    -0.07
    imeline
    -0.07
    纨
    -0.07
    ContentLoaded
    -0.07
    EVENT
    -0.07
    ä½İä¸ĭ头
    -0.07
    BASH
    -0.07
    ziali
    -0.07
    POSITIVE LOGITS
    çIJĨçĶ±æĺ¯
    0.09
    argument
    0.08
    åı¯ä»¥éĢļè¿ĩ
    0.08
     argument
    0.08
    ailleurs
    0.08
    æľĢç®ĢåįķçļĦ
    0.07
    æľĢç®Ģåįķ
    0.07
    åı¯ä»¥çĶ±
    0.07
    æĪĸçĶ±
    0.07
     argumento
    0.07
    Activations Density 0.015%

    No Known Activations