© 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. 1049
    Prev
    Next
    INDEX
    Explanations

    say "http"

    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
     gode
    -0.25
     desar
    -0.24
    HideInInspector
    -0.22
     Bedrooms
    -0.22
    ä¼Ĭæĭī
    -0.21
     Craigslist
    -0.21
     dirent
    -0.20
    çľ¼è¢ĭ
    -0.20
     indeb
    -0.19
     hurd
    -0.19
    POSITIVE LOGITS
     https
    0.80
    https
    0.79
     http
    0.73
    http
    0.68
     www
    0.50
    :http
    0.47
    	http
    0.46
    www
    0.45
    =https
    0.42
    (http
    0.40
    Activations Density 1.425%

    No Known Activations