© 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. 17543
    Prev
    Next
    INDEX
    Explanations

    summing up or total values

    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
    naz
    -0.07
    æľī天
    -0.07
    oir
    -0.07
    Col
    -0.07
    çļĦæľĭåıĭåı¯ä»¥
    -0.07
    ÐIJÐŀ
    -0.07
     jednos
    -0.07
     Pols
    -0.07
    incl
    -0.07
    à¹ģà¸ģà¹Ī
    -0.06
    POSITIVE LOGITS
     nhau
    0.08
    à¸ģัà¸Ļ
    0.08
    çŃīäºİ
    0.08
    åĪ°ä¸Ģèµ·
    0.07
    æĬµ
    0.07
     equals
    0.07
    à¸ģัà¸Ļà¹Ħà¸Ķà¹ī
    0.07
    èĢĮæĪIJçļĦ
    0.07
    æĪIJ为ä¸Ģ个
    0.07
    åĩij
    0.07
    Activations Density 0.009%

    No Known Activations