© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 924
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    è¹ģ
    -0.24
    /GPL
    -0.23
     PartialView
    -0.22
    __':č↵
    -0.22
    onia
    -0.20
    á»ĭa
    -0.20
    oux
    -0.20
    :');↵
    -0.20
    SBATCH
    -0.19
    é̶
    -0.19
    POSITIVE LOGITS
     And
    0.28
    and
    0.26
    çĦ¶åIJİ
    0.24
    And
    0.24
    èĢĮçİ°åľ¨
    0.24
     then
    0.24
     This
    0.24
    èĢĮè¿Ļ
    0.23
     which
    0.22
    which
    0.22
    Activations Density 1.160%

    No Known Activations