© 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. 727
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ToSelector
    -0.26
    FunctionFlags
    -0.24
    TransparentColor
    -0.24
    HeaderCode
    -0.24
    ispens
    -0.24
    geber
    -0.23
    :checked
    -0.22
    Uvs
    -0.21
     Annunci
    -0.21
    loquent
    -0.21
    POSITIVE LOGITS
    对åħ¶çľŁå®ŀ
    0.22
    Mode
    0.21
     Mode
    0.20
    丰æĶ¶
    0.20
     mode
    0.20
    ami
    0.20
    ayer
    0.19
     GURL
    0.19
    mode
    0.18
    飧
    0.18
    Activations Density 0.001%

    No Known Activations