© 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. 58988
    Prev
    Next
    INDEX
    Explanations

    philosophers, writers, and thinkers

    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
     Jep
    -0.07
     Rund
    -0.06
    èĥĨ
    -0.06
    istry
    -0.06
     Scha
    -0.06
    æľ´å®ŀ
    -0.06
    ionali
    -0.06
     Stub
    -0.06
    isto
    -0.06
    äºĨä¸įèµ·
    -0.06
    POSITIVE LOGITS
    çĶŁåij½ä¸ŃçļĦ
    0.08
    apore
    0.08
    erci
    0.08
     loạn
    0.08
    ermen
    0.08
    wir
    0.08
    åİ»åIJ§
    0.07
    çĶŁåij½ä¸Ń
    0.07
      ↵  ↵
    0.07
    .concat
    0.07
    Activations Density 0.004%

    No Known Activations