© 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. 2183
    Prev
    Next
    INDEX
    Explanations

    Dub or First

    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
    ï¼ģ",
    -0.31
    ests
    -0.25
    .LogWarning
    -0.23
     Naughty
    -0.23
    aits
    -0.23
    ÃŃcul
    -0.22
    ï¼ģ');↵
    -0.22
    åįĹæµ·ç½ij
    -0.21
     Nude
    -0.20
    áµī
    -0.20
    POSITIVE LOGITS
     dub
    0.22
    驹
    0.20
    éĶĻäºĨ
    0.20
    =$('#
    0.19
    éĽĨåĽ¢èĤ¡ä»½
    0.19
    ëīĺ
    0.19
    ëIJĺ기
    0.19
    ):?>↵
    0.18
     First
    0.18
    Dub
    0.18
    Activations Density 0.003%

    No Known Activations