© 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-65K
    7. 3061
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
    âĦī
    -0.23
    ðŁĻĤ
    -0.23
    celain
    -0.23
    doÄŁ
    -0.22
    ä¸Ģèĩ´å¥½è¯Ħ
    -0.21
    uç
    -0.21
    –↵↵
    -0.20
    .)↵↵↵↵
    -0.20
    ðŁ¤Ķ
    -0.20
     ×Ķ×ķ×ĵ
    -0.20
    POSITIVE LOGITS
    urry
    0.21
    梳
    0.21
    (compact
    0.21
     enough
    0.20
     doc
    0.20
     DOC
    0.20
    childNodes
    0.20
     Sam
    0.20
    	perror
    0.19
     Cir
    0.19
    Activations Density 0.001%

    No Known Activations