© 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. 687
    Prev
    Next
    INDEX
    Explanations

    mathematical supposition problems

    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
    :numel
    -0.21
    gings
    -0.20
    ÄĪ
    -0.20
    åİ¥
    -0.20
    âĢĴ
    -0.19
    ÄĴ
    -0.19
    -uppercase
    -0.19
    ointed
    -0.18
     vd
    -0.18
     vÃŃde
    -0.18
    POSITIVE LOGITS
    çļĦ带é¢Ĩ
    0.31
    åľ¨è¿ĩ渡
    0.25
    âĦī
    0.23
    åIJįåĪĹåīį
    0.23
    å¤įå·¥å¤į
    0.22
    \OptionsResolver
    0.21
    åı¯ä»¥æĽ´å¥½
    0.21
    .setCode
    0.21
    âŁ
    0.20
    elsif
    0.20
    Activations Density 0.016%

    No Known Activations