© 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. 53142
    Prev
    Next
    INDEX
    Explanations

    United States Court of Appeals circuits

    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
    åħ¥å¸Ĥ
    -0.10
    çݯåį«
    -0.10
    é¦ĸéĥ½
    -0.09
    çĩĶ
    -0.09
    ä¸ŃåĽ½è¶³çIJĥ
    -0.09
    s
    -0.08
    èIJ½åı¶
    -0.08
    åĩ¡æľ¬ç½ij
    -0.08
    Injection
    -0.08
    æĹºçĽĽ
    -0.08
    POSITIVE LOGITS
    uzzi
    0.13
    èľľ
    0.10
    	TokenName
    0.10
    æľīæĿ¡ä»¶çļĦ
    0.09
    ÑĩаÑĤ
    0.09
    è¿Ļæĺ¯åĽłä¸º
    0.09
    è¿Ļæĺ¯æĪij
    0.09
    éħ¿éħĴ
    0.09
    connector
    0.09
    éļĽ
    0.08
    Activations Density 0.165%

    No Known Activations