© 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. 58894
    Prev
    Next
    INDEX
    Explanations

    research literature contrasts

    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
    滿
    -0.07
     cab
    -0.06
    满
    -0.06
    cab
    -0.06
    大åĪ°
    -0.06
     Lula
    -0.06
    头çŃī
    -0.06
    æºĢ
    -0.06
    кви
    -0.06
    å½ĵçĦ¶æĺ¯
    -0.06
    POSITIVE LOGITS
     published
    0.12
     literature
    0.11
    æĸĩçĮ®
    0.11
    æĬ¥éģĵ
    0.10
    -reported
    0.10
    published
    0.10
     reported
    0.10
    reported
    0.09
     unpublished
    0.09
     elsewhere
    0.08
    Activations Density 0.671%

    No Known Activations