© 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. 37460
    Prev
    Next
    INDEX
    Explanations

    speaking, calling, telling

    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
     Prospect
    -0.10
    ê°IJ
    -0.09
    å³Ĵ
    -0.09
    鹧
    -0.09
    [image
    -0.09
    çħĬ
    -0.09
    erman
    -0.09
    éĩĩ
    -0.08
    å¾Ĺ天
    -0.08
    гаÑĢ
    -0.08
    POSITIVE LOGITS
    åijĬè¯īæĪij们
    0.14
    渴
    0.12
    åijĬ
    0.11
    æıIJ示
    0.10
    æľīæĿ¡ä»¶çļĦ
    0.10
    ä¼łæĿ¥
    0.10
    åijĬè¯īæĪij
    0.09
     beck
    0.09
    åijĬè¯īä½ł
    0.09
    èŃ¦ç¤º
    0.09
    Activations Density 0.039%

    No Known Activations