© 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. 7002
    Prev
    Next
    INDEX
    Explanations

    game tag, corruption, overlay, factory, alien, anti, practice

    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
    enk
    -0.07
    aptor
    -0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
    enor
    -0.07
    ÑĽ
    -0.07
    éĢĤåIJĪäºİ
    -0.07
    æĽ´ä¸º
    -0.07
    éĻ¤å¤ĸ
    -0.06
    orer
    -0.06
    acz
    -0.06
    POSITIVE LOGITS
    æĹłéĿŀ
    0.10
     ugyanis
    0.09
     infatti
    0.09
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    0.08
    ãģ¨è¨Ģãģ£ãģ¦ãĤĤ
    0.08
     totiž
    0.08
    åı¯ä¸įæĺ¯
    0.08
     nemlig
    0.08
     Basics
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    Activations Density 0.069%

    No Known Activations