© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26724
    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
    æŁij
    -0.07
    agan
    -0.07
    zd
    -0.07
    åĪ¤
    -0.07
     Eller
    -0.07
    aters
    -0.07
    æĽ´éļ¾
    -0.07
    天æĺİ
    -0.06
    人éģĵ
    -0.06
    ái
    -0.06
    POSITIVE LOGITS
    à¸ļล
    0.08
    æijĺèĩª
    0.07
    mere
    0.07
    ogna
    0.07
    çļĦæľĭåıĭåı¯ä»¥
    0.07
    ä½ĨåĽłä¸º
    0.07
    oming
    0.07
    马å°Ķ
    0.07
    çĿĢèĦ¸
    0.07
    tober
    0.06
    Activations Density 0.000%

    No Known Activations