© 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. 3049
    Prev
    Next
    INDEX
    Explanations

    grief tears

    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
    ãİľ
    -0.24
    räg
    -0.23
    ãİĿ
    -0.23
    Nguá»ĵn
    -0.23
    欣åĸľ
    -0.22
    enties
    -0.22
     mooie
    -0.21
    $LANG
    -0.21
    ulfilled
    -0.20
    ä¹IJ
    -0.20
    POSITIVE LOGITS
     grief
    0.30
    泪
    0.29
     emotion
    0.28
    æĤ¼
    0.28
     emot
    0.28
    bere
    0.28
    æĤ²ä¼¤
    0.27
     tears
    0.27
     emotional
    0.27
    æĥħæĦŁ
    0.27
    Activations Density 0.543%

    No Known Activations