© 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. 65223
    Prev
    Next
    INDEX
    Explanations

    same, similar, identical

    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
    å°ļæľī
    -0.08
    ì£¼ë¡ľ
    -0.08
    erb
    -0.08
    alt
    -0.08
    çļĦé±¼
    -0.07
    å¤
    -0.07
    å°ļ
    -0.07
    ÐĿС
    -0.07
    à¸Ńีà¸ģ
    -0.07
    ENTION
    -0.07
    POSITIVE LOGITS
    缸åIJĮçļĦ
    0.14
    æĺ¯ä¸Ģæł·çļĦ
    0.13
    缸åIJĮ
    0.12
    éĥ½æĺ¯ä¸Ģæł·çļĦ
    0.12
     одина
    0.11
     same
    0.10
    åIJĮæł·çļĦ
    0.10
     identical
    0.10
    éĥ½ä¸Ģæł·
    0.10
    åIJĮä¸Ģ个
    0.09
    Activations Density 0.080%

    No Known Activations