© 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-CHAT-65K
    7. 46329
    Prev
    Next
    INDEX
    Explanations

    woman

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å§Ķç»Ħç»ĩéĥ¨
    -0.25
     siden
    -0.24
    Appending
    -0.24
     Broadcom
    -0.22
    SelectionMode
    -0.21
    morgan
    -0.20
    ç½ijç»ľä¼łæĴŃ
    -0.20
    UITextField
    -0.20
     ogs
    -0.20
    Gender
    -0.20
    POSITIVE LOGITS
    .createClass
    0.29
    (___
    0.28
    companyId
    0.28
    è¿ĶåĽŀæIJľçĭIJ
    0.28
     èĩªåĬ¨çĶŁæĪIJ
    0.27
    Türkiye
    0.26
    ilmington
    0.26
    女æĢ§æľĭåıĭ
    0.26
    _Il
    0.24
    ---</
    0.24
    Activations Density 0.052%

    No Known Activations