© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35927
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
    æĥ³èµ·æĿ¥
    -0.09
    å°±å¤ŁäºĨ
    -0.09
    å¹²äºĭ
    -0.09
    ses
    -0.09
    outed
    -0.09
    å¾Ĺ罪
    -0.08
    éĢłè¡Ģ
    -0.08
    人大
    -0.08
    bound
    -0.08
    å¸ĺ
    -0.08
    POSITIVE LOGITS
    ä¹ŁåĽłæѤ
    0.13
     ÑĤакже
    0.12
    å°¤åħ¶
    0.11
    orem
    0.11
    并ä¸İ
    0.10
    ä¹Łå°Ĩ
    0.10
    åIJĮæĹ¶ä¹Ł
    0.10
    çĶļèĩ³è¿ĺ
    0.10
    åĨ³å¿ĥ
    0.10
    éļıåIJİ
    0.09
    Activations Density 0.095%

    No Known Activations