© 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. 33730
    Prev
    Next
    INDEX
    Explanations

    celebration and activities

    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
    åĨ¬åŃ£
    -0.11
    åĨ¬å¤©
    -0.10
    éĢ¼
    -0.09
     Winter
    -0.09
     winter
    -0.08
    winter
    -0.08
     Christmas
    -0.08
    è¤Ĵ
    -0.08
    maj
    -0.08
    ester
    -0.08
    POSITIVE LOGITS
    è¿Ļä¸Ģ天
    0.16
    å±ĬæŶ
    0.15
    éĤ£ä¸Ģ天
    0.13
    åºĨç¥Ŀ
    0.12
     Activities
    0.10
    éĤ£å¤©
    0.10
    çļĦ主é¢ĺ
    0.10
     festivities
    0.10
    å¾Ģå¹´
    0.10
    ðŁİĤ
    0.10
    Activations Density 0.158%

    No Known Activations