© 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. 60030
    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
    Not in Any Lists

    No Comments

    Negative Logits
    /></
    -0.09
    weiler
    -0.08
    æŃ¤èµ·
    -0.08
    ç¥Ŀä½ł
    -0.08
    cket
    -0.07
    纳
    -0.07
    åĵĩ
    -0.07
    è¿ĺæĺ¯ä¸įéĶĻçļĦ
    -0.07
    irit
    -0.07
    pone
    -0.07
    POSITIVE LOGITS
    ANGAN
    0.07
    缮çļĦ
    0.07
    ELD
    0.07
    جز
    0.07
    issen
    0.07
     purpose
    0.06
    严
    0.06
    ôn
    0.06
    urpose
    0.06
    Purpose
    0.06
    Activations Density 0.000%

    No Known Activations