© 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. 1709
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    缸åħ³è´Łè´£
    -0.30
     èĭ¥è¦ģ
    -0.29
    :request
    -0.28
     iht
    -0.26
     fkk
    -0.25
    )object
    -0.23
    anka
    -0.23
    -fontawesome
    -0.22
    :System
    -0.22
     Fax
    -0.22
    POSITIVE LOGITS
     ISIL
    0.23
    weathermap
    0.21
    .Pages
    0.20
     ============================================================================↵
    0.19
    .IsActive
    0.19
    å¼Ģå¥ĸç»ĵæŀľ
    0.19
    :variables
    0.19
    .page
    0.19
     irq
    0.19
    /operators
    0.19
    Activations Density 0.952%

    No Known Activations