© 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. 38297
    Prev
    Next
    INDEX
    Explanations

    comic books and art

    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
    åĪĴ
    -0.11
    åħ³éĶ®åŃĹ
    -0.10
    æĹħ游å±Ģ
    -0.10
    \Route
    -0.09
    ê¹Į
    -0.09
    ì¶ķ
    -0.09
    çĦ°
    -0.09
    _FATAL
    -0.09
    éªĪ
    -0.08
    éķ¿éķ¿
    -0.08
    POSITIVE LOGITS
    漫çĶ»
    0.12
     Comics
    0.10
     comics
    0.10
    æĨİ
    0.10
     comic
    0.09
    æľŁåĪĬ
    0.09
    墩
    0.09
    å¼Ł
    0.09
    ä¸Ģæľ¬
    0.08
     magazines
    0.08
    Activations Density 0.136%

    No Known Activations