© 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. 16960
    Prev
    Next
    INDEX
    Explanations

    exercisers, children, trilogy, women, group

    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
    ç¥ŀä¹ĭ
    -0.06
     dependent
    -0.06
    har
    -0.06
    åĪ©çĽĬçļĦ
    -0.06
     forgotten
    -0.06
    var
    -0.05
     Nar
    -0.05
     [
    -0.05
    èģĶåIJį
    -0.05
     Plat
    -0.05
    POSITIVE LOGITS
    åģļå¾ĹæĽ´å¥½
    0.09
    ä¸įä»ħåľ¨
    0.09
    æĽ´é«ĺçļĦ
    0.09
    ";}
    0.09
    æĽ´æ³¨éĩį
    0.08
    éļĬ
    0.08
    stä
    0.08
     versa
    0.08
    æľīæĽ´å¤ļçļĦ
    0.08
     ê·¸ëłĩì§Ģ
    0.08
    Activations Density 0.037%

    No Known Activations