© 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. 13271
    Prev
    Next
    INDEX
    Explanations

    normal development

    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
    spur
    -0.08
    å§Ĩæĸ¯
    -0.08
    ť
    -0.08
    uç
    -0.08
    欢声
    -0.07
    ëŀŃ
    -0.07
    ıra
    -0.07
    enga
    -0.07
    aken
    -0.07
    hier
    -0.07
    POSITIVE LOGITS
    ãĢįãĢģãĢĮ
    0.07
    rag
    0.07
    isd
    0.07
     ë¹Ħ롯íķľ
    0.07
    kop
    0.06
    ãĢıãĢİ
    0.06
    è½»éĩį
    0.06
    ä»ĸè¿ĺæĺ¯
    0.06
    _perc
    0.06
     various
    0.06
    Activations Density 0.830%

    No Known Activations