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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1894
    Prev
    Next
    INDEX
    Explanations

    by

    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
    ursal
    -0.27
     licensors
    -0.23
    unitÃł
    -0.23
    çĽ¸ä¿¡å¤§å®¶
    -0.21
    enha
    -0.21
    iesta
    -0.21
    gunakan
    -0.20
    æĬ¹
    -0.19
    ighb
    -0.19
    -picker
    -0.19
    POSITIVE LOGITS
     virtue
    0.40
     means
    0.39
    ,},↵
    0.35
    -products
    0.35
    è¡·
    0.32
    gone
    0.32
     dint
    0.30
    means
    0.30
    -pass
    0.29
     bü
    0.28
    Activations Density 0.714%

    No Known Activations