© 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. 50353
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

    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
    iki
    -0.09
    æĻ®åıĬ
    -0.09
    rench
    -0.09
    ä¸Ģåı¥
    -0.09
    å²ģæŶ
    -0.08
    æĺİæĻº
    -0.08
    çĦī
    -0.08
    年人
    -0.08
     Afr
    -0.08
    æ´Ĵ
    -0.08
    POSITIVE LOGITS
    æīĢåľ¨çļĦ
    0.12
    æīĢåľ¨
    0.11
     ÑħозÑı
    0.11
    æľīè¿Ļæł·çļĦ
    0.10
    主管éĥ¨éŨ
    0.10
    plode
    0.09
    å¹´é¾Ħ段
    0.09
    é«ĺç´łè´¨
    0.09
    åİĦ
    0.09
    ä¸į管
    0.09
    Activations Density 0.076%

    No Known Activations