© 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. 42912
    Prev
    Next
    INDEX
    Explanations

    final / quarter-finals

    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
    ehl
    -0.06
     _
    -0.06
    ected
    -0.06
    IT
    -0.05
    lood
    -0.05
    æĺĻ
    -0.05
     pers
    -0.05
    Arrays
    -0.05
    çݺ
    -0.05
     disruptive
    -0.05
    POSITIVE LOGITS
    æľĢç»ĪçļĦ
    0.10
    æľĢåIJİçļĦ
    0.10
    æľĢåIJİåľ¨
    0.09
     finally
    0.09
    çļĦæľĢç»Ī
    0.09
    æľĢåIJİ
    0.09
     Finally
    0.09
    æľĢåIJİæĺ¯
    0.09
     ë§Īì§Ģë§īìľ¼ë¡ľ
    0.09
    _final
    0.08
    Activations Density 0.004%

    No Known Activations