© 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. 3477
    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
     zro
    -0.21
    ç¼Ń
    -0.20
     bénéficie
    -0.19
    Wolf
    -0.19
    BOSE
    -0.18
    æĭīæĸ¯
    -0.18
    çĺ¸
    -0.18
     <!--[
    -0.18
     anale
    -0.18
    è¡£
    -0.18
    POSITIVE LOGITS
    ãģ¨æĢĿãģ£ãģ¦ãģĦãĤĭ
    0.21
    ilated
    0.21
    -haspopup
    0.21
    seite
    0.19
    linkplain
    0.19
     OnTriggerEnter
    0.19
    InnerText
    0.19
     OnCollision
    0.18
    erialized
    0.18
    sted
    0.18
    Activations Density 0.000%

    No Known Activations