© 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. 1499
    Prev
    Next
    INDEX
    Explanations

    module / modules

    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
    ä»
    -0.07
     grid
    -0.07
     grids
    -0.06
    rokes
    -0.06
     strokes
    -0.06
     deliber
    -0.06
     sino
    -0.06
    è¿ĻæĬĬ
    -0.06
     contest
    -0.06
     Pal
    -0.06
    POSITIVE LOGITS
    าà¸Ļิ
    0.09
    /Peak
    0.09
    _modules
    0.08
    _under
    0.08
    TypeDef
    0.08
    #__
    0.08
    aData
    0.07
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
    çłº
    0.07
    nil
    0.07
    Activations Density 0.029%

    No Known Activations