© 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. 1376
    Prev
    Next
    INDEX
    Explanations

    conditions may be

    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
    æĭľå¸ĪåѦèīº
    -0.26
    nqu
    -0.25
    mouseenter
    -0.24
    zsche
    -0.23
    orget
    -0.23
     roleId
    -0.23
    przed
    -0.22
    achuset
    -0.22
    rir
    -0.22
    ournemouth
    -0.22
    POSITIVE LOGITS
     be
    0.53
     being
    0.42
     бÑĭÑĤÑĮ
    0.39
     been
    0.36
    being
    0.31
    å·²ç»ı被
    0.29
    被
    0.28
     être
    0.28
    être
    0.28
    /w
    0.27
    Activations Density 2.390%

    No Known Activations