© 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. 2247
    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
    azel
    -0.25
     bénéfic
    -0.21
    BOSE
    -0.20
    å¼¥
    -0.20
     myself
    -0.20
    cca
    -0.20
    鸱
    -0.19
    çī©
    -0.18
    !important
    -0.18
    ï¼ģ",
    -0.18
    POSITIVE LOGITS
    åįĥæĸ¹çĻ¾
    0.24
    toDate
    0.23
    \Html
    0.22
     fitte
    0.22
    âĬĬ
    0.22
    åºĹåĬłçĽŁ
    0.21
    ãĤĭãģ¹ãģį
    0.21
    âļĹ
    0.21
     EVT
    0.20
    ///<
    0.20
    Activations Density 0.002%

    No Known Activations