© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9395
    Prev
    Next
    INDEX
    Explanations

    surrender or concede

    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
    adin
    -0.12
    çī¹åĪ«å£°æĺİ
    -0.09
    hoc
    -0.09
    ä¸įäºĪ
    -0.09
    æıIJåĢ¡
    -0.08
    hift
    -0.08
    åĬłä»¥
    -0.08
    worthy
    -0.08
     Firm
    -0.08
    åħ¼
    -0.08
    POSITIVE LOGITS
    ç½®æį¢
    0.09
    è´¨éĩıéĹ®é¢ĺ
    0.09
    /respond
    0.09
    ä¸įäºĨ
    0.09
    aryl
    0.09
    åģ»
    0.09
    äºĨä¸Ģåľº
    0.09
    itte
    0.09
    جÙĨ
    0.08
    ance
    0.08
    Activations Density 0.011%

    No Known Activations