© 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. 5546
    Prev
    Next
    INDEX
    Explanations

    weather conditions

    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
    æĴ
    -0.10
    æĬļ
    -0.09
    æģ¸
    -0.09
    æŀķ
    -0.09
    åĬ¨æĦŁ
    -0.09
    åł°
    -0.09
    åĪ»
    -0.09
    çľ¼çķĮ
    -0.09
    为ä¸Ģä½ĵ
    -0.09
    åIJ¸çº³
    -0.09
    POSITIVE LOGITS
    天æ°Ķ
    0.22
     weather
    0.19
    æĻ´
    0.16
    weather
    0.15
    éĺ³åħī
    0.14
    æ°ĶåĢĻ
    0.13
    Weather
    0.13
     Weather
    0.13
    (weather
    0.12
    _weather
    0.12
    Activations Density 0.086%

    No Known Activations