© 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. 1791
    Prev
    Next
    INDEX
    Explanations

    one and other

    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
    ;base
    -0.34
    lemn
    -0.24
    Ó§
    -0.24
    idar
    -0.24
    /Gate
    -0.24
    printStats
    -0.23
    nces
    -0.23
    uled
    -0.23
    eday
    -0.23
    abox
    -0.23
    POSITIVE LOGITS
     ones
    0.43
    åıįä¹ĭ
    0.40
    åĪĻæĺ¯
    0.39
    åĪĻ
    0.38
    缸åıį
    0.36
     equally
    0.31
    åį´æĺ¯
    0.29
    æĽ´ä¸º
    0.29
    åīĩ
    0.29
    æĽ´å¤ļçļĦæĺ¯
    0.28
    Activations Density 5.188%

    No Known Activations