© 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. 229
    Prev
    Next
    INDEX
    Explanations

    legal and technical documents

    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
     oko
    -0.25
    InView
    -0.25
     nale
    -0.24
    traî
    -0.23
    ç½ijç«Ļé¦ĸ页
    -0.23
     uda
    -0.23
    ç½ijç«Ļåľ°åĽ¾
    -0.22
    åħ¬åijĬ称
    -0.22
    çıħ
    -0.22
    ï¼ģ",
    -0.22
    POSITIVE LOGITS
     metic
    0.28
     siti
    0.28
     bigot
    0.27
     desi
    0.26
     culo
    0.26
     porr
    0.25
    æ°¤
    0.24
     ál
    0.24
     chá
    0.24
     subur
    0.23
    Activations Density 20.825%

    No Known Activations