© 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. 548
    Prev
    Next
    INDEX
    Explanations

    say 'commands'

    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
    Touchable
    -0.24
    èį¤
    -0.22
    áºĴ
    -0.22
    èµ°åĬ¿åĽ¾
    -0.21
    .Args
    -0.21
    åIJ©
    -0.20
    åĶı
    -0.20
    èĢĥèĻijåĪ°
    -0.20
    æłª
    -0.20
    Svg
    -0.20
    POSITIVE LOGITS
    æĸ°å»º
    0.27
    ãİľ
    0.25
    --------------------------------------------------------------------------↵
    0.25
    å¿«æį·
    0.24
     assh
    0.24
     airstrikes
    0.24
    æłı
    0.24
    æīĢæīĢ
    0.23
     {\↵
    0.23
    ฤษ
    0.22
    Activations Density 5.108%

    No Known Activations