© 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. 1126
    Prev
    Next
    INDEX
    Explanations

    program or project

    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
    peror
    -0.30
    strcasecmp
    -0.28
    icester
    -0.28
    )test
    -0.28
    inery
    -0.27
    #ga
    -0.27
    strstr
    -0.27
    :'.$
    -0.26
    elib
    -0.26
    alink
    -0.26
    POSITIVE LOGITS
    ä½ľåĵģ
    0.30
     program
    0.27
     gridColumn
    0.26
     given
    0.25
    产åĵģ
    0.25
     product
    0.24
    é¡¹çĽ®
    0.24
     venir
    0.23
     requestCode
    0.23
     project
    0.23
    Activations Density 6.360%

    No Known Activations