© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17180
    Prev
    Next
    INDEX
    Explanations

    two or pair

    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
     wichtigsten
    -0.08
     grÃ¶ÃŁte
    -0.08
     grÃ¶ÃŁten
    -0.08
     enige
    -0.08
     schönsten
    -0.08
    ä¸ĢåĪĻ
    -0.08
    ä¸Ģ个ç®ĢåįķçļĦ
    -0.08
    æŁIJä¸Ģ
    -0.07
    linger
    -0.07
     ones
    -0.07
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.21
    åı«åģļ
    0.12
    åıĪä¸Ģ个
    0.11
    åIJįåı«
    0.10
    å¤ļæľĪçļĦ
    0.10
    ä»Ģä¹Īæł·çļĦ
    0.10
    æĢİæł·çļĦ
    0.09
     à¤IJसा
    0.09
    èĭ±æĸĩåIJįåŃĹ
    0.09
    æĪĸå¤ļ
    0.08
    Activations Density 0.006%

    No Known Activations