© 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. 44555
    Prev
    Next
    INDEX
    Explanations

    no followed by noun/adjective

    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
    jenigen
    -0.08
    å¿ĹåĪļ
    -0.07
    enticate
    -0.07
    à¸ļาà¸ģ
    -0.07
    ìĩĦ
    -0.07
    æīĢåľ¨çļĦ
    -0.07
     wichtigsten
    -0.07
     most
    -0.07
    Å«k
    -0.07
    æīĭä¸ŃçļĦ
    -0.07
    POSITIVE LOGITS
    /no
    0.10
    æĪĸå°ij
    0.10
    -ever
    0.09
    æıIJä¾Ľä»»ä½ķ
    0.09
    åı¯è¨Ģ
    0.09
     whatsoever
    0.09
    except
    0.09
     obstante
    0.09
    hing
    0.08
     indication
    0.08
    Activations Density 0.065%

    No Known Activations