© 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. 7056
    Prev
    Next
    INDEX
    Explanations

    new business

    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
    éĿŀ常好çļĦ
    -0.11
    ä»ĸèĩªå·±
    -0.11
    åĽłä¸ºå®ĥ
    -0.10
    å¾Ī好çļĦ
    -0.10
    å®īåħ¨ä¿Ŀéļľ
    -0.10
    åľ¨åħ¶
    -0.10
    éĿŀ常å¤ļçļĦ
    -0.10
    缮åīį为æŃ¢
    -0.09
    éĿŀ常å¤ļ
    -0.09
    è¿Ļè¾¹
    -0.09
    POSITIVE LOGITS
    åĽºçĦ¶
    0.14
    å°±æĦıåij³çĿĢ
    0.14
    æĦıåij³çĿĢ
    0.11
     oneself
    0.11
    并ä¸į代表
    0.10
    éĹ®é¢ĺæĺ¯
    0.10
    ä¸į代表
    0.10
    ä¹ĭä½Ļ
    0.10
    çļĦåIJĮæŶ
    0.10
    æľīä½ķ
    0.10
    Activations Density 0.453%

    No Known Activations