© 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. 3207
    Prev
    Next
    INDEX
    Explanations

    div tags

    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
    %X
    -0.34
    apg
    -0.30
    :<?
    -0.28
    ële
    -0.27
    onestly
    -0.27
    repid
    -0.27
    URLException
    -0.27
    odash
    -0.27
    /Dk
    -0.27
    ].'
    -0.26
    POSITIVE LOGITS
    æŁ¥çľĭæĽ´å¤ļ
    0.23
    IFA
    0.22
    é¢ĺ主
    0.21
    class
    0.21
    s
    0.20
    âĸİ
    0.19
    以人æ°ij
    0.19
    解æĶ¾æĢĿæĥ³
    0.19
    çļĦæĪIJéķ¿
    0.19
    æķĪæŀľåĽ¾
    0.19
    Activations Density 0.039%

    No Known Activations