© 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. 37479
    Prev
    Next
    INDEX
    Explanations

    how to showcase

    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
    éĺħè¯»æľ¬æĸĩåīį
    -0.08
    ä¸ĩåĽ½
    -0.08
    大大å°ıå°ıçļĦ
    -0.07
     recens
    -0.07
    ghi
    -0.07
    æĪijæĢķ
    -0.07
    ongyang
    -0.07
    大浪
    -0.07
    ARES
    -0.07
     irgende
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹Īåı«
    0.10
    æľīå¤ļä¹Ī
    0.08
    æĺ¯å¤ļä¹Ī
    0.08
    eh
    0.08
    æľīæŶåĢĻ
    0.08
     betapa
    0.08
    å¦Ĥä½ķçĶ¨
    0.08
     pentingnya
    0.08
     how
    0.07
    çļĦéĩįè¦ģæĢ§
    0.07
    Activations Density 0.220%

    No Known Activations