© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1616
    Prev
    Next
    INDEX
    Explanations

    {

    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
    matchCondition
    -0.28
     }}>{
    -0.26
    oriously
    -0.25
     semiclass
    -0.24
    rvine
    -0.23
    isex
    -0.23
    robat
    -0.23
    ;\">
    -0.23
     strugg
    -0.22
    orical
    -0.22
    POSITIVE LOGITS
    为æĬĵ
    0.28
    aligned
    0.27
    align
    0.25
    ä»İ严治
    0.25
    âĸį
    0.24
    èµ°åĬ¿åĽ¾
    0.23
    é»ijæģ¶
    0.23
    åı¯ä»¥æĽ´å¥½
    0.23
    åľ¨çݩ家
    0.22
     Alignment
    0.22
    Activations Density 0.009%

    No Known Activations