© 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. 4892
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and variables

    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
    åĭĭ
    -0.07
    ä¸Ģ个éĹ®é¢ĺ
    -0.07
    æīĭä¸ĭ
    -0.06
    宦
    -0.06
    å·¥åķĨèģĶ
    -0.06
     ×ij×Ļ×ķתר
    -0.06
    è°ļ
    -0.06
    mlink
    -0.06
    ä¸į说
    -0.06
    itano
    -0.06
    POSITIVE LOGITS
     étant
    0.08
     being
    0.08
     zaÅĽ
    0.08
    åį³
    0.08
    为éļ¾
    0.08
    æĺ¯ä½łçļĦ
    0.07
    angelo
    0.07
    era
    0.07
     fiind
    0.07
    being
    0.07
    Activations Density 0.018%

    No Known Activations