© 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. 39658
    Prev
    Next
    INDEX
    Explanations

    first in sequence or order

    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¨éĥ¨è¯Ħ论
    -0.09
    erged
    -0.08
    æľĢä½İåѦåİĨ
    -0.08
    夥
    -0.08
    å¿ħè¦ģ
    -0.07
    .RESULT
    -0.07
    åIJĪè®®
    -0.07
    æ´Ľå¤«
    -0.07
    èĬį
    -0.07
    åħŃè§Ĵ
    -0.07
    POSITIVE LOGITS
    顺åºı
    0.11
    ä¾Ŀ次
    0.11
     sequentially
    0.10
    ä¾Ŀ次为
    0.10
    åħĪåIJİ
    0.10
     sequential
    0.09
    次åºı
    0.09
    çļĦ顺åºı
    0.09
    Sequential
    0.08
     Sequential
    0.08
    Activations Density 0.103%

    No Known Activations