© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-CHAT-65K
    4. 46181
    Prev
    Next
    INDEX
    Explanations

    read-only property

    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
    _Renderer
    -0.23
     withStyles
    -0.22
     umo
    -0.21
    æĪIJåĬŁçİĩ
    -0.20
    衲
    -0.20
    .Shapes
    -0.20
     correspondent
    -0.19
     po
    -0.19
    andoned
    -0.18
    []>↵
    -0.18
    POSITIVE LOGITS
     perman
    0.25
    editable
    0.22
    panion
    0.20
    \grid
    0.20
    ä¸įå¾Ĺ
    0.20
    æıIJçݰ
    0.20
    .setCancelable
    0.19
    Indexed
    0.19
    Priority
    0.19
     cará
    0.19
    Activations Density 0.147%

    No Known Activations