© 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. 23161
    Prev
    Next
    INDEX
    Explanations

    weather and forecasting information

    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
    æĬ¤çIJĨ
    -0.09
    angkan
    -0.08
    راب
    -0.08
    çĥ«
    -0.08
    Titles
    -0.08
     Harbor
    -0.08
    Reviewer
    -0.08
    ãĤ¤ãĥ¤
    -0.08
    èµİåĽŀ
    -0.07
    eprom
    -0.07
    POSITIVE LOGITS
    æ°Ķ象
    0.18
    é¢ĦæĬ¥
    0.16
    天æ°Ķ
    0.14
     Weather
    0.12
     weather
    0.12
    é«ĺ空
    0.12
    weather
    0.11
    çģ¾å®³
    0.11
    é¢ĦèѦ
    0.11
    å¨ģåĬĽ
    0.11
    Activations Density 0.102%

    No Known Activations