© 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. 1235
    Prev
    Next
    INDEX
    Explanations

    legal document markers

    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
     '.';↵
    -0.22
     milan
    -0.21
     sled
    -0.20
     buc
    -0.19
    -flex
    -0.19
    èľ±
    -0.19
     televis
    -0.19
     fam
    -0.18
    å±ĭ
    -0.18
     pari
    -0.18
    POSITIVE LOGITS
    )(((
    0.23
    )((((
    0.23
    \common
    0.22
     fkk
    0.22
    pheric
    0.22
    ovenant
    0.22
     whiteColor
    0.21
    .lng
    0.21
    outu
    0.21
    {/*
    0.21
    Activations Density 1.450%

    No Known Activations