© 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. 1563
    Prev
    Next
    INDEX
    Explanations

    I / myself

    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
     itself
    -0.40
     themselves
    -0.34
    让æĪij们
    -0.34
    ç»ĻæĪij们
    -0.32
    åijĬè¯īæĪij们
    -0.29
     us
    -0.29
    æĪijä»¬ä¹Ł
    -0.27
     nous
    -0.26
    æĪij们认为
    -0.26
    ç¬ĶèĢħ
    -0.26
    POSITIVE LOGITS
     myself
    0.72
    æĪijèĩªå·±
    0.41
    åĽłä¸ºæĪij
    0.33
    ’m
    0.32
    æĪijçļĦ
    0.30
    'm
    0.30
    说æĪij
    0.29
     могÑĥ
    0.28
     my
    0.28
    /my
    0.28
    Activations Density 4.365%

    No Known Activations