© 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. 1022
    Prev
    Next
    INDEX
    Explanations

    history and time

    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
    -transitional
    -0.22
     meisten
    -0.21
     subparagraph
    -0.21
     unmist
    -0.21
     blowjob
    -0.20
     metic
    -0.20
    -Russian
    -0.20
    oretical
    -0.19
     //----------------
    -0.19
    NavLink
    -0.19
    POSITIVE LOGITS
    /by
    0.28
    gnore
    0.26
     something
    0.25
    /from
    0.25
    ,'#
    0.24
    Hôtel
    0.24
    微软éĽħé»ij
    0.24
    wards
    0.24
    äºĨä¸Ģ
    0.24
     what
    0.23
    Activations Density 5.121%

    No Known Activations