© 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. 4097
    Prev
    Next
    INDEX
    Explanations

    URLs and links

    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
    毫æĹłçĸij
    -0.21
    ');?>
    -0.21
    èĤĵ
    -0.20
    ä»İ严治
    -0.19
     stand
    -0.19
    ðŁijī
    -0.19
     makeStyles
    -0.19
     below
    -0.19
    allas
    -0.19
    ('>
    -0.19
    POSITIVE LOGITS
    exampleModal
    0.23
     ElementType
    0.21
    ampire
    0.20
    importe
    0.20
    storybook
    0.20
     molec
    0.20
    loth
    0.19
     Accord
    0.19
    éķĽ
    0.19
    ertainment
    0.19
    Activations Density 0.383%

    No Known Activations