© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3015
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
    inheritDoc
    -0.23
    佬
    -0.22
     Venez
    -0.20
     mathematical
    -0.20
    éģĽ
    -0.20
    thon
    -0.20
    :".$
    -0.20
    /commons
    -0.19
    .Skin
    -0.19
    æ¼Ķ
    -0.19
    POSITIVE LOGITS
    parated
    0.20
    á¸ı
    0.20
    olkien
    0.20
    çĶĵ
    0.20
    é³Ł
    0.20
    ÄĨ
    0.19
    (always
    0.19
    æ´ģçĻ½
    0.19
    .esp
    0.19
    åĮ
    0.19
    Activations Density 0.158%

    No Known Activations