© 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. 1810
    Prev
    Next
    INDEX
    Explanations

    say "$"

    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
     lawy
    -0.30
    	        ↵
    -0.26
     metic
    -0.24
     (*((
    -0.24
     Jackets
    -0.23
     BuzzFeed
    -0.23
    âĨ¾
    -0.23
     fod
    -0.22
     ['$
    -0.22
     porno
    -0.22
    POSITIVE LOGITS
    __;
    0.32
     $
    0.30
    .);↵
    0.28
    ornment
    0.26
    elerik
    0.26
    (strpos
    0.26
    ãĢĬ
    0.25
    ubbo
    0.25
     `
    0.25
     (){
    0.24
    Activations Density 0.427%

    No Known Activations