© 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. 1783
    Prev
    Next
    INDEX
    Explanations

    but followed by conjunctions

    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
    ultipart
    -0.09
    尽管å¦ĤæѤ
    -0.08
    iglio
    -0.08
    èĻ½çĦ¶æ²¡æľī
    -0.08
     perc
    -0.07
    好ä¸į容æĺĵ
    -0.07
    utable
    -0.07
    empo
    -0.07
    ired
    -0.07
    orce
    -0.07
    POSITIVE LOGITS
    æľªå¿ħ
    0.10
    ston
    0.09
    æŃ»ä¸į
    0.09
    ä¸įä¸Ģå®ļ
    0.08
     ÙĨÛģÛĮÚº
    0.08
     âīł
    0.08
    ä¸į代表
    0.08
    ä¸įåĨįæľī
    0.07
     without
    0.07
    èĢĮä¸į
    0.07
    Activations Density 0.116%

    No Known Activations