© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 650
    Prev
    Next
    INDEX
    Explanations

    monetary amounts

    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
     franca
    -0.23
    .getElementsByName
    -0.22
    潸
    -0.22
    æĽĮ
    -0.22
     commodo
    -0.22
    eko
    -0.20
    #echo
    -0.20
    éĢļ
    -0.20
    haul
    -0.19
    sie
    -0.18
    POSITIVE LOGITS
    (TIM
    0.23
    .intersection
    0.22
    akest
    0.22
    âĸ·
    0.21
    icester
    0.21
    çĸ¬
    0.21
    ,eg
    0.20
    -$
    0.20
    ------+
    0.20
    iyor
    0.20
    Activations Density 0.379%

    No Known Activations