© 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. 24625
    Prev
    Next
    INDEX
    Explanations

    these followed by a noun

    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
    åħ¶äºº
    -0.09
    æŃ¤ä¸º
    -0.08
    ÑİÑĤ
    -0.08
    ship
    -0.08
    水岸
    -0.08
    ÙĬØ©
    -0.07
    ings
    -0.07
    æѤæĸĩ
    -0.07
    ä¸Ģ件äºĭæĥħ
    -0.07
    letcher
    -0.07
    POSITIVE LOGITS
     οÏĢοί
    0.11
     fleste
    0.11
     latter
    0.10
    å¹´æĿ¥
    0.10
    çİ©æĦı
    0.09
    å¹´çļĦ
    0.09
    年被
    0.09
    cond
    0.09
    quiera
    0.09
    å¹´çļĦåıijå±ķ
    0.09
    Activations Density 0.003%

    No Known Activations