© 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. 56386
    Prev
    Next
    INDEX
    Explanations

    new followed by other words

    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
    REA
    -0.06
    ÑĢик
    -0.06
    è¿Ļæĸ¹éĿ¢çļĦ
    -0.06
     Pellegr
    -0.06
    ä¸Ģå®ļç¨ĭ度
    -0.06
    آ
    -0.06
    ranc
    -0.06
    èĩ³ä»Ĭä»į
    -0.06
    第äºĮç±»
    -0.06
    esar
    -0.06
    POSITIVE LOGITS
    sworth
    0.09
    bies
    0.09
    -fashioned
    0.09
    -found
    0.09
    /false
    0.08
    ork
    0.08
    ulkan
    0.08
     /^(
    0.08
    -than
    0.08
    thon
    0.08
    Activations Density 0.052%

    No Known Activations