© 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. 30833
    Prev
    Next
    INDEX
    Explanations

    furthermore, moreover, also

    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
    åį´ä¸įèĥ½
    -0.09
    å¿ħä¸įåı¯å°ijçļĦ
    -0.08
    avras
    -0.08
    åıĹæĥł
    -0.08
    á»ĩt
    -0.08
    Favorites
    -0.07
    å¤ļä¸ĢäºĽ
    -0.07
     bỼt
    -0.07
    åħ¨éĿ¢è´¯å½»èIJ½å®ŀ
    -0.07
    åį´åĽłä¸º
    -0.07
    POSITIVE LOGITS
     tampoco
    0.12
    ãģĿãĤĤãģĿãĤĤ
    0.12
     even
    0.11
    ä¹Łä¸į好
    0.11
     moreover
    0.11
    æĽ´ä¸įèĥ½
    0.10
     sequer
    0.10
     furthermore
    0.10
     Worse
    0.10
    ä¹Łä¸įåIJĮ
    0.10
    Activations Density 0.130%

    No Known Activations