© 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. 31450
    Prev
    Next
    INDEX
    Explanations

    Gettysburg Address

    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
    大éĥ¨ä»½
    -0.08
    bum
    -0.08
    dam
    -0.07
     Dam
    -0.07
    è»Į
    -0.07
    æĺ¯ä¼ģä¸ļ
    -0.07
     CÆ°Æ¡ng
    -0.07
    è¾ħ导åijĺ
    -0.07
    æİĴæ¯Ĵ
    -0.07
    enha
    -0.07
    POSITIVE LOGITS
    å¹½
    0.07
    andle
    0.07
    èĬĻ
    0.06
    课æĸĩ
    0.06
    åħŃä¸ĥ
    0.06
    éĢīèĩª
    0.06
    ç«
    0.06
     readers
    0.06
    è¡£è£Ļ
    0.06
     custom
    0.06
    Activations Density 0.002%

    No Known Activations