© 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. 59089
    Prev
    Next
    INDEX
    Explanations

    email headers and quoted text

    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
    æĺ¯ä¸ĢæīĢ
    -0.09
     numel
    -0.08
     dogg
    -0.08
    ogan
    -0.08
    acey
    -0.08
    æĸĩåįİ
    -0.08
    anjian
    -0.07
    Ð¢Ðł
    -0.07
    onz
    -0.07
    .prevent
    -0.07
    POSITIVE LOGITS
     mailing
    0.10
    éĤ®ä»¶
    0.09
     email
    0.09
     mail
    0.08
     replies
    0.08
     reply
    0.08
    mailto
    0.07
    mail
    0.07
     --
    0.07
    /mail
    0.07
    Activations Density 0.568%

    No Known Activations