© 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. 20893
    Prev
    Next
    INDEX
    Explanations

    possessives like mine and yours

    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
    OMET
    -0.10
    没æľīæĥ³åĪ°
    -0.10
    ä¹Łå¸ĮæľĽ
    -0.09
    代表大ä¼ļ
    -0.09
    å°±è§īå¾Ĺ
    -0.08
    æ´ĭ
    -0.08
    迦
    -0.08
    æŀ·
    -0.08
    æŃ£æĺ¯åĽłä¸º
    -0.08
    åħ±äº«
    -0.08
    POSITIVE LOGITS
     ours
    0.13
     nosotros
    0.11
     yours
    0.11
     theirs
    0.11
     mine
    0.10
     hers
    0.10
     thereof
    0.10
    nya
    0.10
    iniz
    0.10
    ımız
    0.09
    Activations Density 0.034%

    No Known Activations