© 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. 35
    Prev
    Next
    INDEX
    Explanations

    request or argue

    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
     orders
    -0.21
    rÃł
    -0.20
    æµ¥
    -0.19
    optgroup
    -0.19
    .Deep
    -0.18
    ByExample
    -0.18
     Deal
    -0.18
     DRV
    -0.18
    æĿ¡è¯Ħ论
    -0.18
    åĩºå¸Ńä¼ļè®®
    -0.18
    POSITIVE LOGITS
    ä¸»å¼ł
    0.36
    请æ±Ĥ
    0.36
     request
    0.30
    æıIJåĩº
    0.29
     argument
    0.29
    è¯īæ±Ĥ
    0.27
     claim
    0.27
    æıIJ交
    0.27
     requesting
    0.27
     argue
    0.26
    Activations Density 1.205%

    No Known Activations