© 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. 1985
    Prev
    Next
    INDEX
    Explanations

    punctuation and code

    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
     -
    -0.23
    ,
    -0.23
    's
    -0.23
    ...
    -0.22
    çĸĶ
    -0.22
    -
    -0.22
    çļĦéĤ£ä¸Ģ
    -0.22
    çļĦä¸ĢéĿ¢
    -0.21
    çļĦéĤ£ç§į
    -0.21
    --
    -0.21
    POSITIVE LOGITS
     fkk
    0.40
    ?"↵↵↵↵
    0.39
    -Cs
    0.33
    ornment
    0.33
    ".↵↵↵↵
    0.32
    :";č↵
    0.32
    ?";↵
    0.31
    .']
    0.29
    ./(
    0.29
    Intialized
    0.29
    Activations Density 0.219%

    No Known Activations