© 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. 44385
    Prev
    Next
    INDEX
    Explanations

    which introduces explanation

    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
    ecz
    -0.09
    åĽłæѤèĢĮ
    -0.08
     ugyanis
    -0.08
    ÑĬÑİ
    -0.08
    æѤ类
    -0.07
    Æ°á»Ľng
    -0.07
    åĪĩåĭ¿
    -0.07
    ä»ħæıIJä¾Ľ
    -0.07
    chn
    -0.07
    谨记
    -0.07
    POSITIVE LOGITS
    siz
    0.08
    s
    0.08
    izzo
    0.07
    sia
    0.07
    aman
    0.07
    iants
    0.06
    mara
    0.06
    ifu
    0.06
     implies
    0.06
     اÙĦبتÙĩ
    0.06
    Activations Density 0.028%

    No Known Activations