© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6803
    Prev
    Next
    INDEX
    Explanations

    criticizing people or groups

    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
    ç»ıå¼Ģ
    -0.10
    èĩ³åħ³
    -0.09
    çľĭçĤ¹
    -0.09
    游æĪıå½ĵä¸Ń
    -0.09
    人æŃ»äº¡
    -0.09
    æĦŁåıĹåĪ°
    -0.09
    éħ¢
    -0.09
    è¿Ļæł·ä¸Ģ个
    -0.08
    ç»Ŀ
    -0.08
    éĺģ
    -0.08
    POSITIVE LOGITS
    idf
    0.08
     accus
    0.08
    æĩĪ
    0.08
    ä¸įå¤Ł
    0.08
    eil
    0.08
    çģµæ´»æĢ§
    0.08
    çĶ¨äºº
    0.07
    RLF
    0.07
    çĶ¨äºĨ
    0.07
     alleged
    0.07
    Activations Density 0.136%

    No Known Activations