© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10846
    Prev
    Next
    INDEX
    Explanations

    question is answered by

    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
    lips
    -0.09
    ’ai
    -0.08
    ’autres
    -0.08
    æĥķ
    -0.08
    æĽ´æĸ°èĩ³
    -0.08
    [js
    -0.07
    æĪIJæĮĩ
    -0.07
    weig
    -0.07
    ë²Į
    -0.07
    ’)
    -0.07
    POSITIVE LOGITS
    `
    0.08
    ile
    0.06
    åĩij
    0.06
     somehow
    0.06
    åħ´
    0.06
    æĢ»èĢĮè¨Ģä¹ĭ
    0.06
    it
    0.06
    olino
    0.06
    建ç«ĭä¸Ģ个
    0.06
     iler
    0.06
    Activations Density 0.001%

    No Known Activations