© 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. 56455
    Prev
    Next
    INDEX
    Explanations

    protest strike movement sit-in strike

    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
    豺
    -0.09
     punches
    -0.09
     Chess
    -0.09
    çĭ¼
    -0.09
    订è´Ń
    -0.09
    åĨįçĶŁ
    -0.09
     inex
    -0.08
    æķ£æŃ¥
    -0.08
    æĭ³
    -0.08
     Tra
    -0.08
    POSITIVE LOGITS
    æĬĹè®®
    0.13
    ç½¢
    0.10
     protesting
    0.10
     protests
    0.10
    å¸ĪçĶŁ
    0.09
     protest
    0.09
    äºĴèģĶ
    0.09
    æİ¥è¿ŀ
    0.09
    亢
    0.09
    示
    0.09
    Activations Density 0.128%

    No Known Activations