© 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. 8797
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating location

    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
     ÑģÑĤÑĥд
    -0.09
     Moody
    -0.09
    ä½ĵéªĮ
    -0.09
    æĹħè¡Į社
    -0.09
    _ARG
    -0.09
    æľ¬åħ¬åı¸
    -0.09
    为人
    -0.09
    æİīèIJ½
    -0.09
    è§ī
    -0.08
    æĽ´èĥ½
    -0.08
    POSITIVE LOGITS
    åŁİéĩĮ
    0.09
    æ¸İ
    0.09
    å®ĺæĸ¹å¾®åįļ
    0.08
    зван
    0.08
     Lov
    0.08
     burg
    0.08
    æŀ¢çº½
    0.08
    认
    0.08
    ubic
    0.08
     hem
    0.08
    Activations Density 0.112%

    No Known Activations