© 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. 37383
    Prev
    Next
    INDEX
    Explanations

    court names following "the"

    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
    æŃ£å½ĵ
    -0.09
    精彩
    -0.09
    æıŃ
    -0.09
    åIJĪçIJĨ
    -0.09
    åĨ²
    -0.09
    å°ī
    -0.09
    æ¯ĶåĪĨ
    -0.08
    è¦ģåıĬæŶ
    -0.08
     Uncategorized
    -0.08
    ivent
    -0.08
    POSITIVE LOGITS
    pseudo
    0.09
    èĥģ
    0.09
     cord
    0.09
    åħĪçĶŁ
    0.09
    亲çĪ±çļĦ
    0.08
    伪
    0.08
    ssf
    0.08
    éĦĻ
    0.08
    æĪª
    0.08
     Jed
    0.08
    Activations Density 1.123%

    No Known Activations