© 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. 51863
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb/adverb

    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
    allet
    -0.10
    æĪijçĽ¸ä¿¡
    -0.09
    ãģ¾ãģķ
    -0.09
    åıijçİ°èĩªå·±
    -0.09
    åį´åıijçİ°
    -0.09
    Ñģад
    -0.09
    ahan
    -0.09
    ä¸Ģå¾ĭ
    -0.09
     коÑĤоÑĢом
    -0.09
    ä¹ĭæīĢ
    -0.09
    POSITIVE LOGITS
    åıijè´¢
    0.08
    eff
    0.08
    pared
    0.08
    west
    0.08
    æĺ¯å¤ļä¹Ī
    0.08
    inous
    0.08
    æľīæĽ´å¤ļçļĦ
    0.08
    缸åħ³æĶ¿çŃĸ
    0.08
    好åIJĹ
    0.08
     Warp
    0.08
    Activations Density 0.020%

    No Known Activations