© 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. 848
    Prev
    Next
    INDEX
    Explanations

    concepts of power

    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
    à¸ŀัà¸Ļà¸ĺุà¹Į
    -0.08
    kannya
    -0.07
     Globals
    -0.07
    çĦ¶å¤§
    -0.07
    าà¸Ĺ
    -0.07
    atte
    -0.07
     queued
    -0.07
    รัà¸ļà¸ģาร
    -0.07
    icult
    -0.07
    htag
    -0.07
    POSITIVE LOGITS
     wield
    0.11
    power
    0.10
     powers
    0.10
    (power
    0.10
    æĿĥåĬĽçļĦ
    0.10
     power
    0.09
    æĿĥåĬĽ
    0.09
     exercised
    0.09
    /power
    0.09
    à¸Ńำà¸Ļาà¸Ī
    0.08
    Activations Density 0.018%

    No Known Activations