© 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. 58927
    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
    éļĶ
    -0.08
    ione
    -0.07
    inson
    -0.07
    mel
    -0.06
    ijn
    -0.06
     bunk
    -0.06
    ums
    -0.06
    otti
    -0.06
    iss
    -0.06
    lems
    -0.06
    POSITIVE LOGITS
    ä¹Łç½¢
    0.07
    åIJĮæ¯Ķä¸Ĭåįĩ
    0.07
    è¡ħ
    0.07
    çļĦæ¯Ķè¾ĥ
    0.06
    éĿĴ天
    0.06
    软件åĽŃ
    0.06
    èĥģ
    0.06
    udad
    0.06
    xbf
    0.06
    çĬ§çī²
    0.06
    Activations Density 0.000%

    No Known Activations