© 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. 59946
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æŶæĬ¥
    -0.07
    cpt
    -0.06
    oid
    -0.06
    è·µ
    -0.06
    æº
    -0.06
    åįĹèĩ³
    -0.06
    pto
    -0.06
     Benton
    -0.06
     psycholog
    -0.06
    lehr
    -0.06
    POSITIVE LOGITS
    å³
    0.08
    terie
    0.07
    aka
    0.07
    æ´¾åĩº
    0.07
    æ³ĵ
    0.07
    è¯ł
    0.07
    arana
    0.07
    actic
    0.07
    (Op
    0.06
    ãn
    0.06
    Activations Density 0.000%

    No Known Activations