© 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. 20727
    Prev
    Next
    INDEX
    Explanations

    'm, 're, am followed by predicate adjectives or propositions

    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
    带ä¸Ĭ
    -0.09
    èĿĮ
    -0.09
    严
    -0.09
    onation
    -0.08
     hal
    -0.08
     Ling
    -0.08
    ç»ĵ
    -0.08
    lix
    -0.08
     Moral
    -0.08
    æ´Ĺ礼
    -0.08
    POSITIVE LOGITS
    ä¸Ģ个èģĮä¸ļ
    0.11
    PEC
    0.10
    ambia
    0.09
    ä¸įåĨįæĺ¯
    0.09
    è·»
    0.09
    éĤ£è¾¹
    0.09
    åįī
    0.09
    ä¸įåľ¨ä¹İ
    0.09
    alcon
    0.09
    çīĸ
    0.09
    Activations Density 0.064%

    No Known Activations