© 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. 52603
    Prev
    Next
    INDEX
    Explanations

    I'm/I've/I'd followed by verbs/adverbs

    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
    çŁ¥éģĵèĩªå·±
    -0.09
    宣
    -0.08
    å¢Ļå£ģ
    -0.08
    深交
    -0.08
     presum
    -0.08
    æĦŁè°¢
    -0.08
    èµ°å»Ĭ
    -0.08
    ç½ijåıĭ
    -0.08
    为ä¹ĭ
    -0.07
    浪
    -0.07
    POSITIVE LOGITS
    çľĭ好
    0.13
    åİĭå®ŀ
    0.11
    é¢Ħæµĭ
    0.11
    å°±ä¸įä¼ļ
    0.10
    è´Ŀ壳
    0.10
    认为
    0.10
    èī²ç´ł
    0.10
    ç»·
    0.09
    åºķå±Ĥ
    0.09
    çīĩéĿ¢
    0.09
    Activations Density 0.023%

    No Known Activations