© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1003
    Prev
    Next
    INDEX
    Explanations

    word endings

    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
    herits
    -0.33
    INAL
    -0.26
    )=='
    -0.26
    ially
    -0.26
    etine
    -0.25
    lijah
    -0.24
    ='<?
    -0.24
    /Dk
    -0.24
    oriously
    -0.24
    iets
    -0.24
    POSITIVE LOGITS
    ing
    0.74
    ting
    0.47
    ed
    0.47
    ation
    0.46
    ization
    0.45
    ning
    0.42
    ING
    0.41
    isation
    0.39
    ging
    0.39
    ings
    0.37
    Activations Density 3.407%

    No Known Activations