© 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. 3941
    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
     IonicPage
    -0.23
    sworth
    -0.21
     Lage
    -0.20
    ^K
    -0.20
    .writeString
    -0.20
    ÃĶ
    -0.20
    strcasecmp
    -0.20
    èĦ±é¢ĸ
    -0.19
    éĺµ
    -0.19
    prene
    -0.19
    POSITIVE LOGITS
    è¤Ĭ
    0.22
     démarch
    0.21
    quent
    0.20
    orable
    0.20
    fadeOut
    0.19
    éļıæīĭ
    0.19
     çĶŁåij½åij¨æľŁ
    0.19
     pos
    0.19
    ited
    0.19
    ispiel
    0.19
    Activations Density 0.000%

    No Known Activations