© 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. 37625
    Prev
    Next
    INDEX
    Explanations

    ethic, philosophy, poverty

    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
    äs
    -0.07
    éĢĨ
    -0.07
    æĿİåĺī
    -0.06
    ¨
    -0.06
    _ident
    -0.06
    bel
    -0.06
     bel
    -0.06
    æĭī
    -0.06
    -sdk
    -0.06
    udging
    -0.06
    POSITIVE LOGITS
    ×Ļ×ķת
    0.08
    abat
    0.07
    转贴
    0.07
    ãĥŃãĤ¹
    0.07
    gett
    0.07
     fundamentally
    0.07
    ä»Ģä¹Īåı«
    0.07
    æIJŀæ¸ħæ¥ļ
    0.07
    æ¯ģçģŃ
    0.07
    æ°Ķ象åı°
    0.07
    Activations Density 0.368%

    No Known Activations