© 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. 59053
    Prev
    Next
    INDEX
    Explanations

    center, core, central, nucleus

    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
    à¸ļาà¸Ļ
    -0.08
    åIJİè¿ĽçĶŁ
    -0.08
    å¤ĸæĮĤ
    -0.08
    西山
    -0.07
    æĮĤåľ¨
    -0.07
     phai
    -0.07
    ä¸Ĭä¸ĭ游
    -0.07
    verbosity
    -0.07
    ANGAN
    -0.07
    ä¸ļä½ĻæŶéĹ´
    -0.07
    POSITIVE LOGITS
     central
    0.13
    central
    0.11
     centrale
    0.11
    ä¸Ńå¿ĥçļĦ
    0.10
    ä¸Ńå¿ĥ
    0.10
     center
    0.10
     اÙĦÙħرÙĥزÙĬØ©
    0.10
    ä¸Ń央
    0.10
     centrales
    0.10
    为ä¸Ńå¿ĥ
    0.10
    Activations Density 0.045%

    No Known Activations