© 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. 55106
    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
    纳士
    -0.09
    roz
    -0.08
    éĶĻçļĦ
    -0.08
    -www
    -0.08
    EUU
    -0.07
    stum
    -0.07
     âĤ¬*
    -0.07
    heimer
    -0.07
    datatable
    -0.07
    nell
    -0.07
    POSITIVE LOGITS
    ail
    0.08
     ru
    0.07
    婧
    0.06
    idou
    0.06
     Keb
    0.06
    ails
    0.06
    opsis
    0.06
    ç¬ij
    0.06
    è¯Ńæ°Ķ
    0.06
    ailed
    0.06
    Activations Density 0.000%

    No Known Activations