© 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. 4294
    Prev
    Next
    INDEX
    Explanations

    media

    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
    ,");↵
    -0.35
    /Dk
    -0.35
    rippling
    -0.35
    CLUDED
    -0.35
    achinery
    -0.34
    odash
    -0.33
    acerb
    -0.33
    -Compatible
    -0.31
    ingleton
    -0.31
    iferay
    -0.31
    POSITIVE LOGITS
     imageURL
    0.24
    تضÙħÙĨ
    0.23
     imgUrl
    0.23
    -
    0.21
    èĢģ家
    0.21
     nightclub
    0.20
    reopen
    0.20
    /stretch
    0.20
     jap
    0.20
     Brunswick
    0.20
    Activations Density 2.180%

    No Known Activations