© 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. 1946
    Prev
    Next
    INDEX
    Explanations

    word roots

    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
     vert
    -0.21
    Reuse
    -0.20
     fkk
    -0.19
    ******č↵
    -0.19
    íĬľ
    -0.19
    ;display
    -0.19
    .sendStatus
    -0.19
    :[[
    -0.18
    "strconv
    -0.18
    ↵                        ↵
    -0.18
    POSITIVE LOGITS
    ignKey
    0.29
    emade
    0.23
    etz
    0.23
     tremend
    0.22
     maç
    0.22
    ewis
    0.22
    rawid
    0.21
     seiz
    0.21
    -www
    0.21
    perience
    0.21
    Activations Density 0.005%

    No Known Activations