© 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. 4588
    Prev
    Next
    INDEX
    Explanations

    legal and competitive outcomes

    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
    asc
    -0.08
    åŀĭçļĦ
    -0.08
    Gov
    -0.07
    ekar
    -0.07
    ASC
    -0.07
    ala
    -0.07
    è§Ħ模çļĦ
    -0.07
     sweep
    -0.06
    æľīä¸įåIJĮçļĦ
    -0.06
    ibar
    -0.06
    POSITIVE LOGITS
    ׳×ķ
    0.07
    upal
    0.07
    jut
    0.07
    ä»ħæѤ
    0.07
    vinc
    0.07
    erce
    0.07
    wier
    0.07
    iteli
    0.07
    redits
    0.07
    ATAL
    0.07
    Activations Density 0.001%

    No Known Activations