© 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. 46149
    Prev
    Next
    INDEX
    Explanations

    occurrences

    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
    ABCDEFGHIJKLMNOP
    -0.27
     ++)↵
    -0.23
    .mybatisplus
    -0.22
    .TextAlignment
    -0.22
    ormsg
    -0.22
    icter
    -0.22
    avaÅŁ
    -0.21
     MetroFramework
    -0.21
    è¿Ļæī¹
    -0.20
    enuine
    -0.20
    POSITIVE LOGITS
    次æķ°
    0.56
    ä¸ī次
    0.54
    两次
    0.52
    ä¸Ģ次
    0.48
     twice
    0.43
    äºĮ次
    0.42
    åĩłæ¬¡
    0.40
    第ä¸ī次
    0.39
    æľīä¸Ģ次
    0.39
     Twice
    0.37
    Activations Density 0.053%

    No Known Activations