© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2778
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    olatile
    -0.20
    wd
    -0.20
    ibraltar
    -0.20
    lectic
    -0.20
     lodging
    -0.19
     Organ
    -0.19
    esome
    -0.18
    annabin
    -0.18
    ypse
    -0.18
    nze
    -0.18
    POSITIVE LOGITS
    VERRIDE
    0.25
    verture
    0.20
    庸
    0.20
    æ°ijä¼ģ
    0.19
    relude
    0.19
     wann
    0.19
     Venture
    0.19
    æĥĩ
    0.18
    ');"
    0.18
    庶
    0.18
    Activations Density 0.002%

    No Known Activations