© 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. 2705
    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
    éĸ
    -0.23
    boss
    -0.20
    imei
    -0.20
    åħ¨åĬĽä»¥
    -0.19
    IGH
    -0.19
    ippi
    -0.18
    åįĥæĸ¹çĻ¾
    -0.18
    .ta
    -0.17
    éļ¾éģĵ
    -0.17
    wm
    -0.17
    POSITIVE LOGITS
    uerdo
    0.23
     embod
    0.22
    prar
    0.21
    /MIT
    0.20
    Debe
    0.20
    EMPLATE
    0.19
    emsp
    0.19
     bergen
    0.19
    Äĥr
    0.19
     Türk
    0.19
    Activations Density 0.001%

    No Known Activations