© 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. 899
    Prev
    Next
    INDEX
    Explanations

    inflammatory

    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
     automát
    -0.37
     gode
    -0.37
     bergen
    -0.35
    åıĸåĨ³
    -0.34
     esk
    -0.33
     krat
    -0.32
     arrang
    -0.32
     nors
    -0.32
    åľ¨è¿ĩ渡
    -0.31
     desar
    -0.31
    POSITIVE LOGITS
    âļĹ
    0.35
     ÑģенÑĤ
    0.34
    ðŁĵIJ
    0.33
    adoo
    0.32
    .Fat
    0.30
    egov
    0.29
    usaha
    0.29
    juven
    0.29
    skirts
    0.27
    NavController
    0.27
    Activations Density 10.306%

    No Known Activations