© 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. 46452
    Prev
    Next
    INDEX
    Explanations

    D

    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
    女æĢ§æľĭåıĭ
    -0.25
    traî
    -0.24
    .RequestMethod
    -0.23
    åĩºåĽ½çķĻåѦ
    -0.22
     yarg
    -0.21
    EK
    -0.21
    ábado
    -0.21
    æ§ĺãĢħ
    -0.21
    al
    -0.21
     öde
    -0.20
    POSITIVE LOGITS
    itical
    0.25
    Ļ¨
    0.23
    uckets
    0.21
    parer
    0.21
    elerik
    0.20
    ueue
    0.20
    byn
    0.20
    ields
    0.19
    -toggler
    0.19
    erguson
    0.19
    Activations Density 0.009%

    No Known Activations