© 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. 1768
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    ìħ
    -0.25
    .OrderByDescending
    -0.20
     ++)↵
    -0.19
    cest
    -0.19
    ispiel
    -0.19
    zych
    -0.19
    íĤ´
    -0.18
    Orth
    -0.18
     Arc
    -0.18
     cerco
    -0.18
    POSITIVE LOGITS
    imestep
    0.25
    æĹ¥åĩĮæĻ¨
    0.21
    oltip
    0.21
    linky
    0.20
    ented
    0.19
    éĤ¶
    0.19
    eti
    0.19
    AlmostEqual
    0.18
    ëij¬
    0.18
    ëĴĢ
    0.18
    Activations Density 0.708%

    No Known Activations