© 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. 688
    Prev
    Next
    INDEX
    Explanations

    code comments1

    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
     semiclass
    -0.28
    "title
    -0.27
     Ukr
    -0.25
    )(__
    -0.23
    ;o
    -0.23
    -opacity
    -0.23
    $LANG
    -0.23
    "user
    -0.23
    iguiente
    -0.23
    åĪ©çĶ¨æĤ¨çļĦ
    -0.23
    POSITIVE LOGITS
    byss
    0.27
    æѤå¤Ħ
    0.25
     This
    0.24
     TODO
    0.24
    è¿ĻéĩĮæĺ¯
    0.24
     don
    0.23
     if
    0.22
    è¿ĻéĩĮ
    0.22
    ç¡®ä¿Ŀ
    0.21
     this
    0.21
    Activations Density 0.487%

    No Known Activations