© 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. 21382
    Prev
    Next
    INDEX
    Explanations

    relative clause introducer

    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
    骥
    -0.08
     Irving
    -0.08
    é£
    -0.08
    ä¼¼ä¹İ
    -0.08
    好åĥı
    -0.08
     Mighty
    -0.08
    ç»Īäºİ
    -0.08
    åĦĴ
    -0.08
    æľīä»»ä½ķ
    -0.08
    rieve
    -0.07
    POSITIVE LOGITS
    æľ¬èº«å°±
    0.11
     itself
    0.10
    ä¹ŁæŃ£æĺ¯
    0.10
    驹
    0.10
    梧
    0.10
    ä¹Łå°±æĺ¯è¯´
    0.09
    çĶ«
    0.09
    éŃĶçİĭ
    0.09
    æĬĬå®ĥ
    0.08
    æĪIJ为ä¸ĢåIJį
    0.08
    Activations Density 0.320%

    No Known Activations