© 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. 754
    Prev
    Next
    INDEX
    Explanations

    Introduction {#sec}

    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
     mén
    -0.08
    kota
    -0.08
    ä¸ĭä¸ĢæĿ¡
    -0.08
    een
    -0.08
    vá
    -0.07
    rophe
    -0.07
    ÑĦÑĢа
    -0.07
    Exclusive
    -0.07
    anno
    -0.07
    dern
    -0.07
    POSITIVE LOGITS
    è¦ģåĽł
    0.06
    aikan
    0.06
    igy
    0.06
    çĽĬ
    0.06
    teros
    0.06
    boost
    0.06
    ault
    0.06
    noc
    0.06
    æĹłè¾ľ
    0.06
    leit
    0.06
    Activations Density 0.440%

    No Known Activations