© 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. 1249
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis

    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
    esome
    -0.26
    {/*
    -0.26
    apot
    -0.26
    emain
    -0.25
    ].'
    -0.25
     Hã
    -0.25
    otime
    -0.25
    venience
    -0.25
    ï¼Ī
    -0.24
    xon
    -0.24
    POSITIVE LOGITS
    and
    0.27
    æį¢åı¥è¯Ŀ
    0.27
     bli
    0.25
    å¦Ĥæŀľçݩ家
    0.25
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.23
    are
    0.22
    is
    0.22
    Ùª
    0.21
     oran
    0.21
     nok
    0.21
    Activations Density 1.939%

    No Known Activations