© 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. 1306
    Prev
    Next
    INDEX
    Explanations

    medical 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
    #ac
    -0.26
    -Methods
    -0.24
    #aa
    -0.24
    #ab
    -0.24
    #ga
    -0.23
    /Foundation
    -0.22
    并ä¸įæĦıåij³
    -0.22
    .Microsoft
    -0.22
    #af
    -0.22
    -Identifier
    -0.21
    POSITIVE LOGITS
     incarcer
    0.22
     bureaucr
    0.21
     semiclass
    0.18
     Stunning
    0.18
     Erectile
    0.17
     Dumpster
    0.17
     Convenient
    0.17
     */č↵č↵č↵
    0.17
     sophistic
    0.16
     Saudis
    0.16
    Activations Density 98.699%

    No Known Activations