© 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. 839
    Prev
    Next
    INDEX
    Explanations

    to

    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
    bove
    -0.32
    ropri
    -0.31
     sublic
    -0.29
    -transitional
    -0.28
     Erotic
    -0.28
     Strap
    -0.28
    -league
    -0.28
     Millenn
    -0.28
    avigate
    -0.27
     Playoff
    -0.26
    POSITIVE LOGITS
    /from
    0.52
     be
    0.40
    gether
    0.38
    plevel
    0.38
    缮åīį为æŃ¢
    0.37
     whom
    0.36
     the
    0.32
     جاÙĨب
    0.29
     a
    0.27
     which
    0.26
    Activations Density 2.417%

    No Known Activations