© 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. 64520
    Prev
    Next
    INDEX
    Explanations

    produced primarily/mainly

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    æĹłçIJĨçĶ±
    -0.08
    haus
    -0.08
    å°±æĺ¯äºĨ
    -0.07
     kautta
    -0.07
    tron
    -0.07
    tij
    -0.07
    天ä¸ĭ
    -0.07
    èĭ±æīį
    -0.07
    ä»ħæѤ
    -0.07
     ìĿĺíķľ
    -0.07
    POSITIVE LOGITS
     primarily
    0.10
    主è¦ģåľ¨
    0.10
     chiefly
    0.10
    主ãģ«
    0.09
     mainly
    0.09
     ì£¼ë¡ľ
    0.09
     principally
    0.08
    并æĪIJ为
    0.08
    ì£¼ë¡ľ
    0.07
    并äºİ
    0.07
    Activations Density 0.633%

    No Known Activations