© 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. 46300
    Prev
    Next
    INDEX
    Explanations

    poems

    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
    æŁ¥çľĭ详æĥħ
    -0.22
    ç½ijç«Ļé¦ĸ页
    -0.22
    |--------------------------------------------------------------------------↵
    -0.22
     <$
    -0.20
     WithEvents
    -0.20
     Según
    -0.20
    ç½²
    -0.20
     buc
    -0.20
    ÑĨиалÑĮно
    -0.19
    alic
    -0.19
    POSITIVE LOGITS
    iances
    0.22
    ibrary
    0.21
     üzere
    0.20
    oggler
    0.20
    chedulers
    0.20
    黢
    0.20
    /Set
    0.20
    /&
    0.20
    ceive
    0.20
    èĪ·
    0.20
    Activations Density 0.006%

    No Known Activations