© 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. 4361
    Prev
    Next
    INDEX
    Explanations

    previously

    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
    brtc
    -0.26
     }),↵↵
    -0.22
    usra
    -0.22
    ().'/
    -0.21
     }}"><
    -0.20
    trak
    -0.20
    .cf
    -0.20
    -UA
    -0.19
    memcmp
    -0.19
    >Title
    -0.19
    POSITIVE LOGITS
     previously
    0.90
     formerly
    0.73
     Previously
    0.72
    åİŁæĿ¥
    0.69
    以åīį
    0.64
    Previously
    0.63
    æѤåīį
    0.63
    åİŁåħĪ
    0.60
     originally
    0.60
    ä¹ĭåīį
    0.59
    Activations Density 1.195%

    No Known Activations