© 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. 1337
    Prev
    Next
    INDEX
    Explanations

    then followed by "the", "to", or "now"

    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
    éĺ
    -0.07
    yped
    -0.07
    éĹ®ä»ĸ
    -0.07
    书记
    -0.07
    ä¸įèµ·
    -0.06
    /logging
    -0.06
     restarted
    -0.06
    unched
    -0.06
    side
    -0.06
    its
    -0.06
    POSITIVE LOGITS
    åĨįæĬĬ
    0.09
     further
    0.09
    è¿Ľä¸ĢæŃ¥
    0.08
    oku
    0.08
     далÑĮÑĪе
    0.08
    é¡·
    0.07
     далÑĮней
    0.07
    æľŁåĴĮ
    0.07
    antz
    0.07
    éĢ²ä¸ĢæŃ¥
    0.07
    Activations Density 0.006%

    No Known Activations