© 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. 4225
    Prev
    Next
    INDEX
    Explanations

    content

    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
    dration
    -0.22
    éĢı
    -0.20
    elseif
    -0.20
    é¼ĵ
    -0.19
     Christian
    -0.19
     Christ
    -0.19
    opleft
    -0.19
    ("")]↵
    -0.19
     Bild
    -0.19
    reation
    -0.19
    POSITIVE LOGITS
    olicit
    0.23
    .ToShort
    0.22
    nyder
    0.21
    뾨
    0.20
    KHTML
    0.20
     ìŬ룬ë¶Ħ
    0.20
    });↵↵↵↵
    0.20
    -strokes
    0.20
     BuzzFeed
    0.20
     helicopt
    0.19
    Activations Density 0.100%

    No Known Activations