© 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. 1465
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
     beÄŁen
    -0.23
    olest
    -0.23
     èĩªåĬ¨çĶŁæĪIJ
    -0.21
    -uppercase
    -0.21
    -------------</
    -0.20
    ihanna
    -0.20
    :normal
    -0.20
    éĴ³
    -0.19
    èŀŁ
    -0.19
    éĴİ
    -0.19
    POSITIVE LOGITS
     ePub
    0.27
    è§ĨåIJ¬èĬĤ缮
    0.20
    .getFullYear
    0.20
     SpringApplication
    0.19
    å°ıå§IJå§IJ
    0.18
     INCIDENTAL
    0.18
    belt
    0.18
    嵬
    0.18
     FName
    0.18
     GridLayout
    0.18
    Activations Density 0.357%

    No Known Activations