© 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. 29859
    Prev
    Next
    INDEX
    Explanations

    module building process

    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
    ato
    -0.07
     versatile
    -0.07
    åıĬåºĶçĶ¨
    -0.06
    ito
    -0.06
    个
    -0.06
    andi
    -0.06
    anel
    -0.06
    itter
    -0.06
    彷徨
    -0.06
    å¾Ģ
    -0.06
    POSITIVE LOGITS
    ÑħнÑĥÑĤÑĮ
    0.09
    è°ģ说
    0.08
    ä¹Łæĺ¯åįģåĪĨ
    0.08
    vista
    0.08
    ä¸įäºĨçļĦ
    0.08
    nios
    0.08
    åįİéĺ³
    0.08
    _OPTS
    0.08
     '-')
    0.07
    綾
    0.07
    Activations Density 0.618%

    No Known Activations