© 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. 888
    Prev
    Next
    INDEX
    Explanations

    industries and services

    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
     Após
    -0.26
     VERIFY
    -0.21
     Desde
    -0.19
    unit
    -0.19
    Nos
    -0.18
     elseif
    -0.18
    ,unsigned
    -0.18
    à¹Ģà¸Ńà¸ĩ
    -0.18
     @}
    -0.18
    MLS
    -0.18
    POSITIVE LOGITS
    -deals
    0.29
    -valu
    0.28
    ForMember
    0.27
    ilogy
    0.26
    çŃīè¡Įä¸ļ
    0.25
    ;';↵
    0.25
    hế
    0.24
    renom
    0.24
    põe
    0.24
    iá»ĥu
    0.24
    Activations Density 9.541%

    No Known Activations