© 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. 55122
    Prev
    Next
    INDEX
    Explanations

    example after wherein

    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
    æ±Łè·¯
    -0.08
    åºĶäºĪ
    -0.07
    hear
    -0.07
    ظÙĦ
    -0.07
    æľĢç»Ī以
    -0.07
     _)
    -0.07
    ä¸į容
    -0.06
     egent
    -0.06
    lld
    -0.06
    åĵ©
    -0.06
    POSITIVE LOGITS
    çļĦä¾ĭåŃIJ
    0.08
    alas
    0.08
    æŀģ端
    0.07
    à¹Īาà¸ĩ
    0.07
    peÄį
    0.07
    æĢİ麼辦
    0.07
    ãĥĭãĥ³ãĤ°
    0.07
    мп
    0.07
    nde
    0.07
     suppose
    0.07
    Activations Density 0.006%

    No Known Activations