© 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. 65184
    Prev
    Next
    INDEX
    Explanations

    locations and contents

    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
    abort
    -0.08
     abort
    -0.08
     Abort
    -0.07
    æ¢ĵ
    -0.07
    è¾ĵç»Ļ
    -0.07
    èĩªéĢī
    -0.06
    æݥ轨
    -0.06
    xit
    -0.06
    æŁĵ
    -0.06
    æ¦ķ
    -0.06
    POSITIVE LOGITS
    éģ®æĮ¡
    0.13
    éģ®æİ©
    0.12
    å±Ĥå±Ĥ
    0.11
    éĹ´éļĻ
    0.11
    éģ®èĶ½
    0.11
    à¸ļัà¸ĩ
    0.10
    éļľ
    0.10
    éģ®
    0.09
    æİ©
    0.09
    éĩįéĩį
    0.09
    Activations Density 0.159%

    No Known Activations