© 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. 732
    Prev
    Next
    INDEX
    Explanations

    not

    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
     fkk
    -0.32
    /GPL
    -0.31
    ".↵↵↵↵
    -0.30
    âļĹ
    -0.30
    ceptar
    -0.30
    :<?
    -0.29
    ðŁĵIJ
    -0.29
    -With
    -0.29
    ðŁĺī
    -0.29
    /↵↵↵↵
    -0.29
    POSITIVE LOGITS
     necessarily
    0.52
     yet
    0.35
    ches
    0.33
    ori
    0.33
    ched
    0.32
     quite
    0.32
     anymore
    0.29
    زاÙĦ
    0.28
    åķ»
    0.28
     exactly
    0.28
    Activations Density 1.448%

    No Known Activations