© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4352
    Prev
    Next
    INDEX
    Explanations

    overall, whole, entire

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    yth
    -0.23
    ucid
    -0.18
    âݨ
    -0.18
    perimental
    -0.18
     sovere
    -0.18
    iconductor
    -0.18
    <small
    -0.17
    ÐļÑĥпиÑĤÑĮ
    -0.17
    :animated
    -0.17
    lest
    -0.17
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.81
     overall
    0.78
    çļĦæķ´ä½ĵ
    0.74
    æķ´ä¸ª
    0.66
    overall
    0.65
     Overall
    0.65
     whole
    0.64
     entire
    0.63
    æĢ»ä½ĵ
    0.61
    Overall
    0.60
    Activations Density 1.196%

    No Known Activations