© 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. 2947
    Prev
    Next
    INDEX
    Explanations

    say "closing punctuation"

    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
    (defvar
    -0.21
    $/,↵
    -0.20
    uddenly
    -0.20
    ffield
    -0.20
    ænd
    -0.19
    *)"
    -0.19
    )prepare
    -0.19
    /browse
    -0.19
    ’:
    -0.18
    .Debugf
    -0.18
    POSITIVE LOGITS
    ILLISE
    0.22
     Erectile
    0.21
    $where
    0.21
    æľ¬è´¨
    0.20
     "'.
    0.20
    ãĢij,ãĢIJ
    0.19
    uchen
    0.19
    鸡汤
    0.19
    ç»ĵ
    0.18
     Ukr
    0.18
    Activations Density 0.720%

    No Known Activations