© 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. 792
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    reffen
    -0.20
    getDescription
    -0.20
     EntityState
    -0.19
    (Blueprint
    -0.19
    getCell
    -0.19
     bénéfic
    -0.19
    ä¼łè¨Ģ
    -0.18
    âĸ·
    -0.18
    ä»İæł¹æľ¬
    -0.18
    äºĮåŃĹ
    -0.18
    POSITIVE LOGITS
    åĴĮ个人
    0.25
    ungeons
    0.24
    :maj
    0.24
    entifier
    0.24
    irlines
    0.23
    usterity
    0.23
    oftware
    0.23
    åĴĮ社ä¼ļ
    0.23
    swith
    0.22
    ocache
    0.22
    Activations Density 10.720%

    No Known Activations