© 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. 34766
    Prev
    Next
    INDEX
    Explanations

    possessive determiners for objects or groups

    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
    å¤ĩ
    -0.10
    _LD
    -0.10
    çªģåıijäºĭ件
    -0.09
    bia
    -0.09
    IFA
    -0.09
    ä¸įåħ·å¤ĩ
    -0.09
    ÑĮÑİ
    -0.09
    身边çļĦ
    -0.09
    éľį
    -0.08
    éĿ´
    -0.08
    POSITIVE LOGITS
    ç¯ĩç«ł
    0.10
    对åŃ©åŃIJ
    0.08
     wreck
    0.08
    yna
    0.08
    æĻļå¹´
    0.08
    èĦ¸
    0.08
    åľ¨äº¬
    0.08
    åĬłå¼ºå¯¹
    0.08
    etz
    0.08
    yn
    0.08
    Activations Density 0.091%

    No Known Activations