© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 54922
    Prev
    Next
    INDEX
    Explanations

    contrasting states or types

    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
    Negative Logits
    ä¸įåıª
    -0.08
    lein
    -0.07
    ä¸įä¼ij
    -0.07
     reten
    -0.07
    ä¸įæŃ¢
    -0.07
    ÙĨاس
    -0.07
    ä¸įå°½
    -0.07
    ä¸įæĶ¾å¼ĥ
    -0.07
    ä¸įä¸Ģ
    -0.06
    ä¸įä¸Ģå®ļæĺ¯
    -0.06
    POSITIVE LOGITS
    æĹłä»»ä½ķ
    0.12
     neither
    0.11
    å®Įåħ¨æ²¡æľī
    0.11
    ä¸įä¼ļ产çĶŁ
    0.11
    ä¸įåħ·å¤ĩ
    0.11
    ä¸įåħ·æľī
    0.11
     Neither
    0.10
     lacks
    0.10
     keinerlei
    0.10
     à¹Ħมà¹Īมี
    0.10
    Activations Density 0.063%

    No Known Activations