© 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. 30555
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

    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
    ç§ī
    -0.09
    å®Ľ
    -0.09
    主è¦ģåİŁåĽł
    -0.09
    mare
    -0.09
    æĪ¿è½¦
    -0.09
    инÑĤеÑĢ
    -0.08
    ä»Ģä¹Īä¸ľè¥¿
    -0.08
    åѤåĦ¿
    -0.08
     determin
    -0.08
    ç¾¤å²Ľ
    -0.08
    POSITIVE LOGITS
     counterparts
    0.15
     counterpart
    0.11
     predecessors
    0.09
    åīįè¾Ī
    0.09
    preced
    0.09
    å®ĥçļĦ
    0.09
    ä»ĸ们çļĦ
    0.09
    _initialized
    0.09
    æľĭåıĭ们
    0.09
    åīį身
    0.08
    Activations Density 0.052%

    No Known Activations