© 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. 3618
    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
    egral
    -0.21
    黢
    -0.21
     *)[
    -0.21
    elaide
    -0.20
    çĩİ
    -0.20
    .QLabel
    -0.19
    osc
    -0.19
    =\"/
    -0.19
     acomp
    -0.19
    atatype
    -0.19
    POSITIVE LOGITS
     bergen
    0.21
    ifestyles
    0.21
    économ
    0.20
    orraine
    0.19
    Ä®
    0.19
    (strpos
    0.19
    è°¢éĤĢ
    0.19
     sez
    0.19
    лив
    0.18
    plusplus
    0.18
    Activations Density 0.000%

    No Known Activations