© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18138
    Prev
    Next
    INDEX
    Explanations

    weather research and forecasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æī©
    -0.10
    ç»Ĭ
    -0.09
     vig
    -0.08
    綦
    -0.08
    หวาà¸Ļ
    -0.08
    vincial
    -0.08
    å¼ł
    -0.08
    éĿ¢ä¸´
    -0.08
    loyd
    -0.08
     Mechanics
    -0.08
    POSITIVE LOGITS
     weather
    0.14
    天æ°Ķ
    0.13
    æ°ĶåĢĻ
    0.13
     Weather
    0.13
    /weather
    0.12
    weather
    0.11
    (weather
    0.11
    æ°Ķ象
    0.10
    ä¹İ
    0.10
    Weather
    0.10
    Activations Density 0.051%

    No Known Activations