© 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. 13066
    Prev
    Next
    INDEX
    Explanations

    information, deadline, limits, recent, documents, won, open, install

    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
    ardino
    -0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.08
    ÙĦÙĪÙĦ
    -0.08
    wyn
    -0.08
    è¿Ľä¸ĢæŃ¥æݨåĬ¨
    -0.07
    Äħcz
    -0.07
     ALSO
    -0.07
    wa
    -0.07
    erva
    -0.07
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.07
    POSITIVE LOGITS
     however
    0.07
    大马
    0.07
    ioni
    0.07
    íħĮ
    0.07
    åĬ£
    0.06
     nond
    0.06
    æ®ĭ
    0.06
     пова
    0.06
    however
    0.06
    acor
    0.06
    Activations Density 2.573%

    No Known Activations