© 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. 472
    Prev
    Next
    INDEX
    Explanations

    document headers

    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
    -END
    -0.21
    ä¹ĭ称
    -0.21
     (![
    -0.20
    )((((
    -0.19
    ë³į
    -0.19
    bbie
    -0.19
    ABSPATH
    -0.19
    çĽ¹
    -0.18
    .EXTRA
    -0.18
     Dzi
    -0.18
    POSITIVE LOGITS
     *----------------------------------------------------------------
    0.24
    ervo
    0.19
     Pant
    0.19
    ä¸įå¿ĺ
    0.19
    hil
    0.19
     Vac
    0.19
     imgUrl
    0.19
    éģį
    0.18
    åıĪ好åıĪå¿«
    0.18
     ↵		↵
    0.18
    Activations Density 0.011%

    No Known Activations