© 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. 56922
    Prev
    Next
    INDEX
    Explanations

    own possessives

    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
    åĨ³èĥľ
    -0.09
    人家
    -0.08
    大家
    -0.08
    ream
    -0.08
    fare
    -0.08
    ä»İæł¹æľ¬
    -0.08
    ä¸į代表
    -0.08
     اÙĦØ®ÙĦÙĬ
    -0.08
    /oct
    -0.08
    大家éĥ½
    -0.08
    POSITIVE LOGITS
    ä¸į足
    0.10
    亲æīĭ
    0.09
     behalf
    0.09
    çĹĤ
    0.09
    çİĭèĢħ
    0.08
    æĥĬ人
    0.08
    èIJ½åIJİ
    0.08
    å¥ĩ迹
    0.08
    ä¸įåı¯
    0.08
    å°ıå°ıçļĦ
    0.08
    Activations Density 0.013%

    No Known Activations