© 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. 853
    Prev
    Next
    INDEX
    Explanations

    plural or possessive

    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
    å±Ĥåĩºä¸į
    -0.38
     subparagraph
    -0.37
    çļĦä¸Ģ款
    -0.31
     DAMAGES
    -0.30
    个å¤ļå°ıæŶ
    -0.30
    åķģ
    -0.29
     OTHERWISE
    -0.29
     +=↵
    -0.28
     TORT
    -0.27
    -scalable
    -0.27
    POSITIVE LOGITS
    们éĥ½
    0.52
    们çļĦ
    0.52
    们
    0.49
    åĢij
    0.36
     ones
    0.34
    pciones
    0.34
    ses
    0.32
    xes
    0.32
    ées
    0.30
     ragazze
    0.29
    Activations Density 11.788%

    No Known Activations