© 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. 31226
    Prev
    Next
    INDEX
    Explanations

    references, citations, bibliography

    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
    çĭ¸
    -0.08
    ä¸įå®ļ
    -0.08
    çĮķ
    -0.07
    è§Ħ模为
    -0.07
    该æ¡Ī
    -0.07
    relude
    -0.07
    ä¸İä¼Ĺ
    -0.07
     Alegre
    -0.07
    æīĢ为
    -0.07
    ç¹¼çºĮéĸ±è®Ģ
    -0.07
    POSITIVE LOGITS
    éıĪ
    0.07
    ict
    0.07
    ify
    0.07
    loom
    0.07
     credible
    0.06
    软
    0.06
    æĿĥå¨ģ
    0.06
    vec
    0.06
     Ùħعت
    0.06
     Bios
    0.06
    Activations Density 0.006%

    No Known Activations