© 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. 2793
    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
    gnore
    -0.23
    ">ÃĹ</
    -0.23
    ortex
    -0.22
    ï½ŀ↵↵
    -0.21
    .getHours
    -0.20
    åħ¶æīĢ
    -0.20
    ynos
    -0.19
    ácil
    -0.19
    ä¸ĭ游
    -0.19
    macen
    -0.19
    POSITIVE LOGITS
    thinkable
    0.27
     ((__
    0.24
    WebResponse
    0.22
    tier
    0.21
    åī¯åİ¿éķ¿
    0.21
    /MIT
    0.20
     }},↵
    0.20
    rå
    0.20
    éĴŃ
    0.20
    ifetime
    0.20
    Activations Density 0.000%

    No Known Activations