© 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. 32188
    Prev
    Next
    INDEX
    Explanations

    definitely, totally, fully, strictly

    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
     تÙĤرÙĬب
    -0.11
     almost
    -0.10
     hampir
    -0.08
    almost
    -0.08
     nicht
    -0.08
    ä¸įçĶĺ
    -0.08
     duly
    -0.08
     essentially
    -0.08
    åĩłä¹İéĥ½æĺ¯
    -0.08
     virtually
    -0.08
    POSITIVE LOGITS
    ä½Ĩåı¯ä»¥
    0.10
     anymore
    0.09
    ëĤĺë§Ī
    0.09
    èĢĮæĺ¯
    0.09
     sondern
    0.09
    /full
    0.08
    ä½Ĩèĩ³å°ij
    0.08
     lắm
    0.08
    หรà¸Ńà¸ģ
    0.08
    ä¹Łä¸įä¸Ģå®ļ
    0.08
    Activations Density 0.061%

    No Known Activations