© 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. 4341
    Prev
    Next
    INDEX
    Explanations

    program

    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
     w
    -0.29
    w
    -0.27
     post
    -0.26
    er
    -0.26
     on
    -0.26
     set
    -0.25
    _
    -0.24
     close
    -0.24
     dis
    -0.24
     do
    -0.24
    POSITIVE LOGITS
    .CustomButton
    0.41
    -deals
    0.40
     Millenn
    0.40
     libertine
    0.38
    /animations
    0.38
     lokale
    0.37
     Noticed
    0.37
     vö
    0.36
     Interracial
    0.36
     bureaucr
    0.36
    Activations Density 0.063%

    No Known Activations