© 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. 51584
    Prev
    Next
    INDEX
    Explanations

    Star Wars and DC Comics themes

    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
    éķ£
    -0.09
    obot
    -0.09
    idente
    -0.09
    Escape
    -0.09
    æijĦ
    -0.09
    æİ°
    -0.08
     Volk
    -0.08
    jej
    -0.08
    lot
    -0.08
     nymph
    -0.08
    POSITIVE LOGITS
     swords
    0.10
    çħľ
    0.09
     sword
    0.09
    çłį
    0.09
    æĮ¥
    0.09
    åĨĹ
    0.09
    æŃ¦å£«
    0.08
    æ²ı
    0.08
    åĦ¿åŃIJ
    0.08
    çĶŁæĹ¥
    0.08
    Activations Density 0.081%

    No Known Activations