© 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. 1287
    Prev
    Next
    INDEX
    Explanations

    #

    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
    微软éĽħé»ij
    -0.22
    æģ«
    -0.20
    RYPTO
    -0.20
    é¾ĩ
    -0.20
    AGIC
    -0.20
    -lnd
    -0.20
    lotte
    -0.19
    inscription
    -0.19
    (pl
    -0.19
     erotica
    -0.19
    POSITIVE LOGITS
     section
    0.36
    section
    0.33
     Section
    0.29
    _section
    0.28
     subsection
    0.28
     SECTION
    0.28
     sections
    0.28
    subsection
    0.27
    .section
    0.27
    -section
    0.23
    Activations Density 0.272%

    No Known Activations