© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38350
    Prev
    Next
    INDEX
    Explanations

    risk communication and decision-making

    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
    çļĦçľ¼ç¥ŀ
    -0.09
    çª
    -0.09
    离
    -0.09
    ä¸ķ
    -0.09
    æį»
    -0.09
    æİł
    -0.09
    åī¥
    -0.09
    inth
    -0.09
    è·Ŀ
    -0.09
    è¿ĺæĺ¯è¦ģ
    -0.09
    POSITIVE LOGITS
    çIJĨæĢ§
    0.09
    é£İéĻ©
    0.09
     Mog
    0.09
    cert
    0.09
     Snap
    0.09
    大å¥ĸ
    0.09
    çļĦé£İéĻ©
    0.09
    åIJ¬å®Į
    0.09
     ep
    0.08
    æĶ¾å¿ĥ
    0.08
    Activations Density 0.106%

    No Known Activations