© 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. 833
    Prev
    Next
    INDEX
    Explanations

    put

    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
    wards
    -0.26
     setFrame
    -0.23
    smouth
    -0.23
    ç¾İåªĴ
    -0.22
    luet
    -0.21
     abdom
    -0.21
    ,err
    -0.20
    ĻĤ
    -0.20
     seiz
    -0.20
    wner
    -0.20
    POSITIVE LOGITS
     out
    0.47
     into
    0.44
     up
    0.43
     down
    0.39
     off
    0.38
     onto
    0.37
     back
    0.34
     aside
    0.33
    into
    0.33
     away
    0.33
    Activations Density 3.174%

    No Known Activations