© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5061
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs in questions

    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
    èĻ½çĦ¶
    -0.09
    ä¹ĭæīĢ以
    -0.09
    大å§IJ
    -0.08
    æĿijæĿijæ°ij
    -0.08
    并ä¸įæĺ¯
    -0.08
    èĥİ
    -0.08
    èĻ½çĦ¶æĺ¯
    -0.08
    ensor
    -0.08
    Ñīен
    -0.08
    çĿ
    -0.07
    POSITIVE LOGITS
    æĪijä»¬åľ¨
    0.15
    æĪij们
    0.13
    æĪijåĢij
    0.13
    æĪij们è¦ģ
    0.13
    æĪij们å°Ĩ
    0.12
    æĪij们çļĦ
    0.12
    å®ĥ们
    0.12
    人们
    0.11
    æĪij们åı¯ä»¥
    0.11
     we
    0.11
    Activations Density 0.114%

    No Known Activations