© 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. 936
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
    usterity
    -0.25
    bove
    -0.24
    è¿ijæĹ¥
    -0.23
    æĺİæĹ¥
    -0.22
    atak
    -0.22
     sodom
    -0.22
    ä»ĬæĻļ
    -0.21
    âĬĬ
    -0.21
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.20
    æĺ¨æĹ¥
    -0.20
    POSITIVE LOGITS
     when
    0.28
    çļĦæŶåĢĻ
    0.26
     coinc
    0.24
    when
    0.23
    :view
    0.21
    èļ±
    0.21
    大éĥ¨åĪĨ人
    0.21
    toPromise
    0.21
    çļĦæĻĤåĢĻ
    0.21
    äºĨ好åĩł
    0.21
    Activations Density 2.429%

    No Known Activations