© 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. 55190
    Prev
    Next
    INDEX
    Explanations

    numbers following punctuation

    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
    ecker
    -0.08
    ä¸įéĹ®
    -0.08
     "&#
    -0.07
    enaar
    -0.07
    å§Ĩæĸ¯
    -0.07
    ilyn
    -0.07
    ä¸ĢéĹ®
    -0.07
    à¦Ĥশ
    -0.07
     domanda
    -0.07
    reo
    -0.06
    POSITIVE LOGITS
    abra
    0.08
    phant
    0.08
    ãģŁãģ£ãģ¦
    0.07
    æ·ij
    0.07
    essions
    0.06
    eden
    0.06
    èĮħ
    0.06
    outh
    0.06
    undert
    0.06
    ë©į
    0.06
    Activations Density 0.004%

    No Known Activations