© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16859
    Prev
    Next
    INDEX
    Explanations

    emergency services and situations

    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
    ounty
    -0.09
    elay
    -0.09
    éĢį
    -0.08
    åĨįéĢł
    -0.08
    æĦıæĦ¿
    -0.08
    å¤ļå°ij
    -0.08
    Spoiler
    -0.08
    è¯Ŀ说
    -0.08
    è¤Ĵ
    -0.08
    /uploads
    -0.08
    POSITIVE LOGITS
    ç´§æĢ¥
    0.24
     emergencies
    0.19
    åºĶæĢ¥
    0.19
     emergency
    0.19
    emergency
    0.17
    æĢ¥æķij
    0.14
     Emergency
    0.14
    çªģåıijäºĭ件
    0.13
    åħ³éĶ®æŶåĪ»
    0.13
    çī¹æ®ĬæĥħåĨµ
    0.13
    Activations Density 0.058%

    No Known Activations