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. 30-TRANSCODER-HP
    4. 15266
    Prev
    Next
    INDEX
    Explanations

    vent or ventilation

    np_max-act-logits · 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
     sideline
    -0.28
     adam
    -0.27
    ctrine
    -0.25
     audible
    -0.24
     bicy
    -0.24
     paw
    -0.24
    ç»ĦåĽ¾
    -0.24
     histograms
    -0.23
     pedestrian
    -0.23
    weise
    -0.23
    POSITIVE LOGITS
    eon
    0.29
    oti
    0.26
    uer
    0.26
    gin
    0.26
     Bodies
    0.26
    rax
    0.26
    efd
    0.26
    æĩĭ
    0.26
    askan
    0.25
    èĢĥæł¸
    0.25
    Activations Density 0.105%

    No Known Activations