© 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. 46414
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    -strokes
    -0.29
    /stretch
    -0.26
     proprié
    -0.24
     bigot
    -0.23
    odash
    -0.23
    herits
    -0.23
    iferay
    -0.22
    plemented
    -0.22
    EMPL
    -0.22
    вÑĢеменно
    -0.22
    POSITIVE LOGITS
    es
    0.22
    ä¸į让
    0.20
    缮å½ķ
    0.19
    кÑĢÑĭл
    0.19
     Sources
    0.19
     deleteUser
    0.18
    æĭĬ
    0.18
     Cham
    0.18
    ong
    0.18
    ex
    0.18
    Activations Density 0.000%

    No Known Activations