© 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. 47486
    Prev
    Next
    INDEX
    Explanations

    fact that, say that, point out that

    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
    人马
    -0.08
    มà¸Ļ
    -0.08
    ier
    -0.08
    åijĺ
    -0.08
    รม
    -0.07
    åı¯èĥ½å°±
    -0.07
    ä½łæľĢ
    -0.07
     "/",
    -0.07
    ny
    -0.07
    ÑĥмÑĭ
    -0.07
    POSITIVE LOGITS
     bahwa
    0.21
     rằng
    0.19
     that
    0.17
     bahawa
    0.15
     ÏĮÏĦι
    0.14
    that
    0.14
     daÃŁ
    0.13
     dass
    0.12
     Ú©Ùĩ
    0.12
     Ø£ÙĨ
    0.12
    Activations Density 0.713%

    No Known Activations