© 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. 55643
    Prev
    Next
    INDEX
    Explanations

    weather updates and forecast

    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
    .MaxLength
    -0.09
    å·¡
    -0.08
    ria
    -0.08
    wan
    -0.08
    è¸ı
    -0.08
    éķģ
    -0.08
    Stamp
    -0.08
    agon
    -0.08
    ister
    -0.08
    åį§
    -0.08
    POSITIVE LOGITS
    天æ°Ķ
    0.30
     weather
    0.25
    weather
    0.21
    æ°ĶåĢĻ
    0.20
    æĻ´
    0.19
     Weather
    0.19
    (weather
    0.19
    Weather
    0.18
    /weather
    0.18
    _weather
    0.17
    Activations Density 0.080%

    No Known Activations