© 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. 45959
    Prev
    Next
    INDEX
    Explanations

    high school, autumn season

    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
    ä¹ĭåĪĿ
    -0.10
     пеÑĢво
    -0.09
    ä¸Ģå¼Ģå§ĭ
    -0.09
    åĪĿè§ģ
    -0.09
    èµ·æŃ¥
    -0.09
    åĪĿæľŁ
    -0.09
     Initial
    -0.09
     INITIAL
    -0.08
    æľĢåĪĿçļĦ
    -0.08
    .Initial
    -0.08
    POSITIVE LOGITS
    æľĢåIJİä¸Ģ个
    0.17
    æľĢåIJİä¸Ģ
    0.16
    æľ«æľŁ
    0.13
    æľ«
    0.12
    çļĦæľĢåIJİ
    0.12
     terakhir
    0.11
    æľĢåIJİä¸Ģ天
    0.11
    -last
    0.11
     ë§Īì§Ģë§ī
    0.11
    ç»Īç»ĵ
    0.11
    Activations Density 0.112%

    No Known Activations