© 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. 2993
    Prev
    Next
    INDEX
    Explanations

    weight loss

    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
    aeda
    -0.21
    iteit
    -0.21
    .newaxis
    -0.20
     ServiceException
    -0.20
    pip
    -0.20
     @{$
    -0.20
    )((((
    -0.19
    .simps
    -0.19
    å°¥
    -0.19
     jMenuItem
    -0.19
    POSITIVE LOGITS
    çĶŁæ´»æĸ¹å¼ı
    0.23
    å¡ij
    0.23
     weight
    0.22
    åĩıèĤ¥
    0.22
    ä¸¥æł¼
    0.21
    ideshow
    0.21
    ä½ĵéĩį
    0.21
     lifestyle
    0.20
    strict
    0.20
    ãĥĢãĤ¤ãĤ¨
    0.20
    Activations Density 0.313%

    No Known Activations