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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36960
    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
    éĽªå±±
    -0.11
    ç´¯äºĨ
    -0.10
    æīª
    -0.10
    å¤ĸæı´
    -0.10
    èĪĢ
    -0.10
    æ¹®
    -0.09
    æºĥ
    -0.09
    ëIJĺë©´
    -0.09
    è¿Ļéĥ¨åĪĨ
    -0.09
    æĶ¾è¿ĩ
    -0.09
    POSITIVE LOGITS
    å½ĵ天
    0.10
    åĮĹ大
    0.08
    ìĥī
    0.08
     Kah
    0.08
    uard
    0.08
    ä¸Ģ天
    0.08
    åĨ·
    0.08
    使å¾Ĺ
    0.08
    æŶä¸įæŶ
    0.08
    olland
    0.08
    Activations Density 0.041%

    No Known Activations