© 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. 65016
    Prev
    Next
    INDEX
    Explanations

    math equations and technical jargon

    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
    æłijä¸Ģ
    -0.08
    ctic
    -0.08
    çīĩæľº
    -0.08
    anzas
    -0.08
    å¡Ĭ
    -0.08
    åħ¶è¡Į为
    -0.07
    大ä¸ĸçķĮ
    -0.07
    agher
    -0.07
    arnya
    -0.07
    lahan
    -0.07
    POSITIVE LOGITS
     betreffenden
    0.07
    g
    0.07
    åľ¨å¹³æŶ
    0.07
    è¾ĥçŁŃ
    0.07
    -related
    0.07
    trys
    0.06
    erii
    0.06
    tang
    0.06
     segment
    0.06
    ç»Ļ大家åĪĨ享
    0.06
    Activations Density 0.001%

    No Known Activations