© 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. 45961
    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
    æģĻ
    -0.21
     ControllerBase
    -0.21
    rams
    -0.19
    æĭĽå¾ħ
    -0.19
    æݪ
    -0.19
    æIJŀ
    -0.19
    诳
    -0.19
    elier
    -0.19
     QText
    -0.18
    榴
    -0.18
    POSITIVE LOGITS
     ******************************************************************************/↵↵
    0.24
    StandardItem
    0.23
    ÑĤÑĢад
    0.21
    ê»Ģ
    0.21
    .utf
    0.21
     newcom
    0.20
    tÃł
    0.20
    æ¦Ķ
    0.20
    íħIJ
    0.20
     masturbating
    0.20
    Activations Density 0.000%

    No Known Activations