© 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. 46249
    Prev
    Next
    INDEX
    Explanations

    classifying things

    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
     Playstation
    -0.34
     tremend
    -0.32
     dieta
    -0.31
     rookies
    -0.31
     traged
    -0.29
     veter
    -0.29
     NSUInteger
    -0.29
    æ¸ħçĪ½
    -0.28
     rewind
    -0.28
     girlfriends
    -0.28
    POSITIVE LOGITS
    traî
    0.44
     çĶŁåij½åij¨æľŁ
    0.36
     MediaTek
    0.36
    gnore
    0.35
    '+↵
    0.35
    åķIJ
    0.35
    åıĪ好åıĪ
    0.34
    åĻĺ
    0.34
     suç
    0.34
    åĹ«
    0.34
    Activations Density 4.268%

    No Known Activations