© 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. 1874
    Prev
    Next
    INDEX
    Explanations

    medical/scientific 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
    lève
    -0.24
     meille
    -0.24
    èĴ¡
    -0.24
    ');?></
    -0.23
     a
    -0.23
    ed
    -0.22
    åıĹä¸įäºĨ
    -0.21
    æijĩäºĨ
    -0.21
     “
    -0.21
     kısa
    -0.20
    POSITIVE LOGITS
     tats
    0.37
     disadv
    0.35
    niest
    0.29
     busty
    0.29
     ×Ķ×ķ×ĵ
    0.29
    EGIN
    0.28
     dicks
    0.28
     bureaucr
    0.27
     fucks
    0.27
     swingers
    0.26
    Activations Density 13.187%

    No Known Activations