© 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. 34811
    Prev
    Next
    INDEX
    Explanations

    conclude or implies what is likely

    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
    fras
    -0.08
    羨
    -0.08
    羡
    -0.08
    ä¸ĩåıĺ
    -0.07
    åı¯ä»¥æıIJä¾Ľ
    -0.07
    ancam
    -0.07
    Pid
    -0.07
    ifs
    -0.07
    []{
    -0.07
    kees
    -0.07
    POSITIVE LOGITS
     somehow
    0.09
    èĩ³å°ijåľ¨
    0.09
    å¿ħé¡»
    0.09
     either
    0.09
     entweder
    0.08
    è¦ģä¹Ī
    0.08
     must
    0.08
     Either
    0.08
    å¿ħé¡»åħĪ
    0.08
    å¿ħé¡»çĶ±
    0.08
    Activations Density 0.012%

    No Known Activations