© 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. 65008
    Prev
    Next
    INDEX
    Explanations

    section delimiters

    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
    ÙĦع
    -0.08
    uhi
    -0.07
    ssc
    -0.07
    رز
    -0.07
    valueOf
    -0.07
    üp
    -0.07
    ehm
    -0.07
    /vendor
    -0.07
     "{}
    -0.07
    è¶ħé«ĺ
    -0.07
    POSITIVE LOGITS
    à¹Ģสà¸Ļ
    0.07
    鸳
    0.07
     Duffy
    0.07
    å¾ħ
    0.07
     ES
    0.06
    âĢ§
    0.06
    è®¤çľŁç»Ħç»ĩ
    0.06
    à¸ļุà¸į
    0.06
     اÛĮÙħ
    0.06
     sabar
    0.06
    Activations Density 0.038%

    No Known Activations