© 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. 54071
    Prev
    Next
    INDEX
    Explanations

    wholly-owned subsidiary companies

    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
     поÑĤ
    -0.10
    客æĪ·éľĢæ±Ĥ
    -0.09
    æ³ķå®ĺ
    -0.09
    åĿij
    -0.09
    æIJľç´¢å¼ķæĵİ
    -0.09
    缺åı£
    -0.08
    æ´ĭæ´ĭ
    -0.08
    ä¸Ģåı£
    -0.08
    å¯Ĥ
    -0.08
    第ä¸ĢèĬĤ
    -0.08
    POSITIVE LOGITS
    éĻĦå±ŀ
    0.12
    æݧèĤ¡
    0.12
     subsidiaries
    0.11
    åIJĪèµĦåħ¬åı¸
    0.11
    íļĮìĤ¬
    0.11
     subsidiary
    0.11
    åħ¨èµĦ
    0.10
    åŃIJåħ¬åı¸
    0.10
    ç»ıèIJ¥
    0.10
    åħ¨èµĦåŃIJ
    0.09
    Activations Density 0.148%

    No Known Activations