© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3326
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    crast
    -0.21
    :black
    -0.20
     *</
    -0.20
    wüns
    -0.20
    çľĭçĶµè§Ĩ
    -0.20
    ...");↵↵
    -0.20
    matchCondition
    -0.20
    tty
    -0.19
    .namespace
    -0.19
    ivic
    -0.19
    POSITIVE LOGITS
    ajes
    0.20
    ä¸ĢåĢĭ人
    0.19
    Mathf
    0.19
    elor
    0.19
    odes
    0.19
    ownt
    0.19
    cação
    0.18
    dw
    0.18
    toLocale
    0.18
    libft
    0.18
    Activations Density 0.007%

    No Known Activations