© 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. 44495
    Prev
    Next
    INDEX
    Explanations

    discharge, mapping, education

    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
    à¹Ĩ
    -0.07
    es
    -0.07
    大æĪIJ
    -0.07
    ÅĤ
    -0.06
    lessly
    -0.06
    á»ĩn
    -0.06
    ably
    -0.06
    an
    -0.06
    ere
    -0.06
    ually
    -0.06
    POSITIVE LOGITS
     Insg
    0.09
    .lu
    0.08
    mund
    0.08
    PELL
    0.08
    å¾ĭå¸ĪäºĭåĬ¡æīĢå¾ĭå¸Ī
    0.08
    .nom
    0.08
    ëģ¼
    0.08
    rated
    0.08
    éĩijé¦Ļ
    0.08
    headed
    0.08
    Activations Density 0.049%

    No Known Activations