© 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. 63730
    Prev
    Next
    INDEX
    Explanations

    etc, login, electrodes, Giving, implemented

    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
    åī©ä½ĻçļĦ
    -0.09
    żu
    -0.08
    åĽłä¸ºä½ł
    -0.08
     sogenannten
    -0.07
     tzw
    -0.07
    åĮºåŁŁåĨħçļĦ
    -0.07
     sogenannte
    -0.07
    alise
    -0.07
    æĽ´åĬłæĸ¹ä¾¿
    -0.07
     Dustin
    -0.07
    POSITIVE LOGITS
    éļ¶
    0.07
    åħ³äºİæĪij们
    0.07
     centr
    0.07
    terer
    0.07
    ardless
    0.07
     etc
    0.07
    éĥ½æľīäºĨ
    0.07
     mellett
    0.06
    ä¸įéĹ®
    0.06
    atitude
    0.06
    Activations Density 0.022%

    No Known Activations