© 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. 21500
    Prev
    Next
    INDEX
    Explanations

    conjunctions or sentence starters following punctuation

    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
    以便
    -0.09
    iate
    -0.09
    å¿ħçĦ¶ä¼ļ
    -0.09
    å¿ħè¦ģ
    -0.08
    æľīåĬ©
    -0.08
    ãĤĪãģĭãģ£ãģŁ
    -0.08
    çĿ½
    -0.08
    ç»ĩ
    -0.08
    å¿ħçĦ¶
    -0.08
    çĶŁæ´»çļĦ
    -0.08
    POSITIVE LOGITS
    åĽłæѤ
    0.13
     therefore
    0.11
    æīĢä»¥åľ¨
    0.10
    æĢİä¹ĪåĬŀ
    0.10
    æīĢ以æĪij们
    0.10
    æīĢ以说
    0.10
    æīĢ以æĪij
    0.09
    ä¸į稳å®ļ
    0.09
    Therefore
    0.09
    æīĢ以
    0.09
    Activations Density 0.213%

    No Known Activations