© 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. 55432
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitions

    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
    apé
    -0.07
    ãģ£ãģ¦ãģĦãģ¾ãģĻãģĮ
    -0.07
    ainless
    -0.07
    åŁ¹è®Ńæ´»åĬ¨
    -0.07
     _______,
    -0.07
    ESCO
    -0.07
    elec
    -0.06
    çļĦçģµéŃĤ
    -0.06
    为æĬĵæīĭ
    -0.06
    ä¸įä»ħæĺ¯
    -0.06
    POSITIVE LOGITS
     moreover
    0.08
     furthermore
    0.08
    åĽłæѤèĢĮ
    0.07
     consequently
    0.07
    åIJİèĢħ
    0.07
    åĽłèĢĮ
    0.07
     subsequently
    0.07
     appunto
    0.07
    òi
    0.07
     بدÙĪرÙĩ
    0.07
    Activations Density 1.723%

    No Known Activations