© 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. 19251
    Prev
    Next
    INDEX
    Explanations

    that followed by a noun or pronoun

    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
    asm
    -0.09
    itas
    -0.09
     ÙĪاÙĦÙģ
    -0.08
    åħ¶å®ĥéĹ®é¢ĺ
    -0.08
    _PREF
    -0.08
    åİĺ
    -0.08
    å¦ĤæĦı
    -0.08
     Ø°ÙĪ
    -0.08
    çijĹ
    -0.08
    olie
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.14
    çİ©æĦı
    0.12
     latter
    0.10
    岸
    0.10
    è¿Ļä¸ĢçĤ¹
    0.09
    便æĺ¯
    0.09
    家ä¼Ļ
    0.09
    éĽĨä¸Ń
    0.09
    继æī¿
    0.09
    éĤ£æł·çļĦ
    0.09
    Activations Density 0.151%

    No Known Activations