© 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. 20749
    Prev
    Next
    INDEX
    Explanations

    Chesterton, Usher, Bennett, Hour

    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
    æ±ķ
    -0.06
    .EventHandler
    -0.06
    etro
    -0.06
     Fargo
    -0.06
    è¯Ń
    -0.05
    åħ¶åİŁåĽł
    -0.05
     COPYING
    -0.05
    -HT
    -0.05
    éŁ³æłĩ
    -0.05
     ÑĤÑĢа
    -0.05
    POSITIVE LOGITS
     teatr
    0.08
    oppable
    0.08
    å¤ĩæ¡Īåı·
    0.07
    ÙĦÙĬÙĩ
    0.07
    ä¼ĺåĮĸèIJ¥åķĨçݯå¢ĥ
    0.07
    áĢ°
    0.07
    vfs
    0.07
    èµŀè¿ĩ
    0.07
    sache
    0.07
    ìļ°ë¦¬
    0.07
    Activations Density 0.134%

    No Known Activations