© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59067
    Prev
    Next
    INDEX
    Explanations

    syntax-only print options

    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
    Negative Logits
    ĤŃ
    -0.08
    çķĮéĻIJ
    -0.07
    WhiteSpace
    -0.06
    ä¿©
    -0.06
    both
    -0.06
    owa
    -0.06
    iko
    -0.06
    ÙĤد
    -0.06
    hdr
    -0.06
    toa
    -0.06
    POSITIVE LOGITS
    éĢī项ä¸Ń
    0.11
     options
    0.10
    éĢīæĭ©é¢ĺ
    0.10
    åºĶéĢīæĭ©
    0.09
    åľ¨éĢīæĭ©
    0.09
    æĿ¥éĢīæĭ©
    0.09
    éģ¸æĬŀèĤ¢
    0.09
     Options
    0.09
    éĢī项
    0.09
    è¦ģéĢīæĭ©
    0.09
    Activations Density 0.018%

    No Known Activations