© 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. 42
    Prev
    Next
    INDEX
    Explanations

    date ranges

    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
    *)((
    -0.23
    !("{
    -0.21
    âķ³
    -0.20
    BEGIN
    -0.20
    -AA
    -0.19
    ()."
    -0.18
    евиÑĩ
    -0.18
    ä¸Ģç¬ij
    -0.18
    {name
    -0.17
     QQ
    -0.17
    POSITIVE LOGITS
    为æŃ¢
    0.25
    icensing
    0.23
    VILLE
    0.22
    alborg
    0.21
    尽头
    0.21
    åĨįåĪ°
    0.21
     Breitbart
    0.21
    æľ«ç«¯
    0.21
    æŃ¢
    0.21
    ">ÃĹ</
    0.21
    Activations Density 1.134%

    No Known Activations