© 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. 877
    Prev
    Next
    INDEX
    Explanations

    legal and official news

    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
    çļĦ带é¢Ĩ
    -0.34
    éĿŀ常çļĦ
    -0.34
    Whilst
    -0.31
     erotica
    -0.30
    (
    -0.29
    /
    -0.26
     nextState
    -0.25
    éļĨéĩį举è¡Į
    -0.25
     locksmith
    -0.25
     disadv
    -0.25
    POSITIVE LOGITS
    /Area
    0.32
     çĶŁåij½åij¨æľŁ
    0.29
    _Api
    0.29
    DETAIL
    0.28
    %X
    0.28
    Ỹ
    0.28
    :disable
    0.28
    /inet
    0.27
     amid
    0.27
    %f
    0.27
    Activations Density 10.925%

    No Known Activations