© 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. 1404
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ='<?
    -0.24
    -await
    -0.23
    ãĥĥãĤ·ãĥ¥
    -0.21
    éªľ
    -0.21
    &);↵↵
    -0.20
    herits
    -0.20
    ÐŁÐµÑĤеÑĢбÑĥÑĢ
    -0.20
    ;top
    -0.20
    xaf
    -0.19
    .squareup
    -0.19
    POSITIVE LOGITS
    aptops
    0.25
     pp
    0.24
     issue
    0.23
    æĹ¥æ¶Īæģ¯
    0.22
     Issue
    0.22
    autiful
    0.21
    年第
    0.20
    (nonatomic
    0.20
    uggage
    0.20
    .issue
    0.19
    Activations Density 0.210%

    No Known Activations