© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 484
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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
    SharedPtr
    -0.50
    reffen
    -0.31
     Shirt
    -0.30
    OLLOW
    -0.29
    Ø¥ÙħÙĥاÙĨ
    -0.27
    болезн
    -0.26
    ÙĨÙģØ°
    -0.26
    rophy
    -0.25
    ätig
    -0.25
    تغÙĬر
    -0.25
    POSITIVE LOGITS
    oulouse
    0.37
    ertiary
    0.30
    سÙĦØŃ
    0.28
    /false
    0.27
    -Shirt
    0.27
    ÙĨتشر
    0.26
    intégr
    0.25
    nosis
    0.23
    eresa
    0.23
    urtles
    0.23
    Activations Density 4.658%

    No Known Activations