© 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. 52231
    Prev
    Next
    INDEX
    Explanations

    genetic engineering, diversity, typing, variation, programming, strain

    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
    er
    -0.13
    تÙĨ
    -0.09
    eri
    -0.08
    ر
    -0.08
    å½¹
    -0.07
     giud
    -0.07
    çĦ¶å¤§
    -0.07
    ment
    -0.07
    auté
    -0.07
    anging
    -0.07
    POSITIVE LOGITS
    ually
    0.11
    /gen
    0.11
    åįļçī©éĻ¢
    0.10
    lify
    0.09
    apolis
    0.08
    สà¹Į
    0.08
    ãģĹãĤī
    0.08
    ically
    0.08
    ists
    0.08
    omic
    0.08
    Activations Density 0.025%

    No Known Activations