© 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. 36915
    Prev
    Next
    INDEX
    Explanations

    clauses introduced by "that"

    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
    å½ĵä½ł
    -0.12
     باÙĦÙĨسبة
    -0.10
    åľ¨è¿Ļ个
    -0.09
    å½ĵæĪij们
    -0.09
    å¦Ĥæŀľè¯´
    -0.08
    éĢIJ
    -0.08
    èĤĥ
    -0.08
    ĺ认
    -0.08
    .leading
    -0.08
    åĤį
    -0.08
    POSITIVE LOGITS
     it
    0.10
    å®ĥæĺ¯
    0.09
    æľīæīĢ
    0.09
    æĺ¯æľĢ好çļĦ
    0.09
    çļĦåīįæıIJ
    0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    0.08
    inton
    0.08
    çķ´
    0.08
    elsen
    0.08
     they
    0.08
    Activations Density 0.115%

    No Known Activations