© 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. 2403
    Prev
    Next
    INDEX
    Explanations

    official actions

    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
    éĺį
    -0.23
     OnTrigger
    -0.22
    äºĵ
    -0.20
    _TestCase
    -0.20
     Bild
    -0.19
    .say
    -0.19
    []{↵
    -0.19
     explicitly
    -0.19
    cie
    -0.19
    cour
    -0.19
    POSITIVE LOGITS
     citiz
    0.22
     collegiate
    0.21
    )$_
    0.21
    "';
    0.21
    .ClientSize
    0.20
    QWidget
    0.20
    èµ·çłģ
    0.20
    åĸģ
    0.20
    âĴ¸
    0.20
     Tmax
    0.20
    Activations Density 0.927%

    No Known Activations