© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62913
    Prev
    Next
    INDEX
    Explanations

    documents that are primarily technical, legal, or formal text with specialized formatting and terminology.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jrosseruk
    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
    tig
    -0.08
    å¿
    -0.07
    Licensed
    -0.07
    ä¹Łåı¯ä»¥æĺ¯
    -0.07
    _DISP
    -0.07
    æľĢå¥½åľ¨
    -0.07
    }):
    -0.07
    å¿«éĢŁçļĦ
    -0.07
    CTYPE
    -0.07
     Aran
    -0.07
    POSITIVE LOGITS
    åīį款
    0.07
    产åѦ
    0.07
    elen
    0.07
     correctly
    0.07
     rounds
    0.06
    med
    0.06
    è°ĥçĶ¨
    0.06
    缸åħ³è´Łè´£äººè¡¨ç¤º
    0.06
    产åīį
    0.06
     correctness
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.