© 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. 2869
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    np_max-act-logits · gemini-2.5-flash-lite
    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
    upported
    -0.24
    /Instruction
    -0.22
    /fontawesome
    -0.21
    /Internal
    -0.21
    æºĺ
    -0.20
    ìĿį
    -0.20
     pérd
    -0.20
    (___
    -0.20
    icens
    -0.19
     createState
    -0.19
    POSITIVE LOGITS
    brahim
    0.21
    vers
    0.21
     ÃĹ
    0.21
     noc
    0.20
    ayah
    0.20
     /
    0.20
    pageNum
    0.20
    åĬŀå®ŀäºĭ
    0.19
     vs
    0.19
    æĬ¢
    0.19
    Activations Density 0.388%

    No Known Activations