© 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. 56852
    Prev
    Next
    INDEX
    Explanations

    power outages and emergency calls

    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
    çĹĬ
    -0.10
    åħħæ²Ľ
    -0.09
    æĺ¥é£İ
    -0.09
    鼶件
    -0.08
    æ´ĹåĩĢ
    -0.08
    ç¹ģå¿Ļ
    -0.08
    å¼Ģå·¥
    -0.08
    oron
    -0.08
    æ··
    -0.08
    å©Ģ
    -0.08
    POSITIVE LOGITS
    INI
    0.10
    ä¼ĺåħĪ
    0.10
    ekt
    0.09
    åıijçĶµæľº
    0.09
    Tier
    0.09
    éŀħ
    0.09
    è½®
    0.09
    exo
    0.09
    é¦ĸè½®
    0.09
    ä¸Ģè½®
    0.09
    Activations Density 0.042%

    No Known Activations