© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 780
    Prev
    Next
    INDEX
    Explanations

    patent numbers

    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
    -Semit
    -0.24
    ")!=
    -0.24
    è¿Ļ个èģĮä¸ļ
    -0.23
    ctal
    -0.21
    ĵį
    -0.21
    åĻĻ
    -0.20
    éĥĥ
    -0.20
    æĤŃ
    -0.20
     strdup
    -0.20
     även
    -0.20
    POSITIVE LOGITS
    erÃł
    0.23
    ,No
    0.22
    çī¹æĸ¯
    0.21
     ÐłÐµÑģп
    0.21
    ou
    0.20
    åı·
    0.20
    ;\↵
    0.20
    .parentElement
    0.19
     ÐŁÐ¾Ñĩем
    0.19
    fühl
    0.19
    Activations Density 1.019%

    No Known Activations