© 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. 46702
    Prev
    Next
    INDEX
    Explanations

    wise/wisdom

    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
    bsites
    -0.24
    indered
    -0.20
    vasive
    -0.20
    cheiden
    -0.19
     Standard
    -0.19
    ersion
    -0.18
    innitus
    -0.18
    ibraltar
    -0.18
    หà¸Ńม
    -0.18
    Standard
    -0.18
    POSITIVE LOGITS
     wisdom
    0.41
    wis
    0.34
    æĻºæħ§
    0.34
     Wisdom
    0.33
     wise
    0.31
    Wis
    0.30
    WISE
    0.29
    æĻº
    0.26
     Wise
    0.25
    oracle
    0.24
    Activations Density 0.037%

    No Known Activations