© 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. 44695
    Prev
    Next
    INDEX
    Explanations

    technical terms ending with -ically or -ical

    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
    onen
    -0.08
    ertas
    -0.07
    å¥½å·¥ä½ľ
    -0.07
    以åıĬå¦Ĥä½ķ
    -0.07
    pawn
    -0.06
    è¿Ń
    -0.06
    abyrin
    -0.06
     (“
    -0.06
    ">&#
    -0.06
    并为
    -0.06
    POSITIVE LOGITS
    éĻ¤å¤ĸ
    0.10
    çļĦéĤ£ç§į
    0.10
     thereof
    0.10
     wise
    0.09
    çīĪ
    0.08
    å±ħå¤ļ
    0.08
    éĹ·
    0.07
    ä¹Łè¡Į
    0.07
    åĽĽå¤§
    0.07
    ä¹Łç½¢
    0.07
    Activations Density 0.225%

    No Known Activations