© 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. 7300
    Prev
    Next
    INDEX
    Explanations

    sequence after operator or symbol

    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
    garan
    -0.08
    溢
    -0.08
    byname
    -0.07
     Barros
    -0.07
    druck
    -0.07
     ÐĿали
    -0.07
     stimmen
    -0.07
    .currentThread
    -0.07
    agh
    -0.07
     Nou
    -0.07
    POSITIVE LOGITS
    luck
    0.08
    åľ¨åIJĦç§į
    0.08
    ç¼ĸ
    0.07
    è°ĥ
    0.06
     av
    0.06
    illet
    0.06
    ovac
    0.06
     Ay
    0.06
    ä¸ĢæĮĩ
    0.06
    毡
    0.06
    Activations Density 0.039%

    No Known Activations