© 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. 56908
    Prev
    Next
    INDEX
    Explanations

    automatically followed by an action

    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
    aner
    -0.09
    antro
    -0.08
     вообÑīе
    -0.08
     wirklich
    -0.08
    æľĢç»Ī以
    -0.08
     decidedly
    -0.08
     оÑĤдÑĭ
    -0.08
    主è¦ģç»ıèIJ¥
    -0.08
    åħ·ä½ĵæݪæĸ½
    -0.08
    andola
    -0.08
    POSITIVE LOGITS
    èĩªåĭķçļĦãģ«
    0.11
    èĩªåĬ¨
    0.10
     automatically
    0.10
     automatic
    0.09
    -automatic
    0.09
    ãģĹãĤĤ
    0.09
     automatico
    0.09
    Automatic
    0.08
     تÙĤرÙĬب
    0.08
    Ùĭ
    0.08
    Activations Density 0.035%

    No Known Activations