© 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. 44311
    Prev
    Next
    INDEX
    Explanations

    mimicry, predator, dead, competition

    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
    è·ij
    -0.07
    éķ¿æŀª
    -0.07
     smoothly
    -0.06
    fre
    -0.06
    åŀ®
    -0.06
     haf
    -0.06
    æĪ»
    -0.06
    åĨ³å®ļçĿĢ
    -0.06
    ellan
    -0.06
    æ¶Įåħ¥
    -0.06
    POSITIVE LOGITS
     deterrent
    0.10
    /display
    0.09
    -display
    0.09
    å¨ģæħij
    0.09
    ä¿ĿæĬ¤èĩªå·±
    0.09
     predator
    0.09
     displays
    0.09
    ä¿ĿæĬ¤èĩªå·±çļĦ
    0.09
    å¼ķ诱
    0.08
    ä¿ĿæĬ¤æ³ķ
    0.08
    Activations Density 0.035%

    No Known Activations