© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 176
    Prev
    Next
    INDEX
    Explanations

    business or commerce

    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/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :animated
    -0.24
    \grid
    -0.22
    usra
    -0.22
     nigeria
    -0.22
    à¹Ĥà¸Ĩ
    -0.22
    .NewRequest
    -0.21
    ë´ħ
    -0.21
    IPH
    -0.21
     piger
    -0.20
    [:]
    -0.20
    POSITIVE LOGITS
    åįĴ
    0.23
    ıyla
    0.22
     IonicPage
    0.20
     üz
    0.19
    MC
    0.18
    yectos
    0.17
    ibur
    0.17
     MC
    0.17
    ä¸īåĽ½
    0.17
    æ±Ĩ
    0.17
    Activations Density 0.001%

    No Known Activations