Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 23-TRANSCODER-HP
    4. 162235
    Prev
    Next
    INDEX
    Explanations

    Tropical weather/locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
     hookers
    -0.26
    çαç¾İ
    -0.26
     flown
    -0.24
    äºĮç»´
    -0.24
    apers
    -0.24
    msp
    -0.24
    kowski
    -0.24
    sert
    -0.24
     McGill
    -0.24
    .edu
    -0.23
    POSITIVE LOGITS
    çĵ¦
    0.27
    iae
    0.26
       
    0.25
    ANEL
    0.25
    ath
    0.25
    enna
    0.24
     Stevenson
    0.24
    anes
    0.24
    orrow
    0.24
    weather
    0.24
    Activations Density 0.001%

    No Known Activations