© 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. 52074
    Prev
    Next
    INDEX
    Explanations

    copyright followed by year

    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
     rumpe
    -0.08
    \\/
    -0.08
    auce
    -0.08
    åħ¬åı¸æĭ¥æľī
    -0.08
    amac
    -0.08
    .".
    -0.08
    cier
    -0.07
    头åı·
    -0.07
     دÙĬر
    -0.07
    Ú©ÙĨ
    -0.07
    POSITIVE LOGITS
    at
    0.06
    æİ
    0.06
    æį·
    0.06
    anyi
    0.06
    ä¸Ĭè¡Į
    0.06
    顺
    0.06
    wo
    0.06
    inata
    0.05
    以èĩªå·±
    0.05
     nháºŃt
    0.05
    Activations Density 0.252%

    No Known Activations