© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53840
    Prev
    Next
    INDEX
    Explanations

    manga and chapter titles

    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
    å·¢
    -0.10
    åħ¨è¦ĨçĽĸ
    -0.09
     ìŀħìŀ¥
    -0.08
     Kale
    -0.08
     erk
    -0.08
    åħ»
    -0.08
    羣åģĩ
    -0.08
    è°±
    -0.08
     Neh
    -0.08
    妫
    -0.08
    POSITIVE LOGITS
    漫çĶ»
    0.13
    è¿ŀè½½
    0.11
     Manga
    0.10
     manga
    0.10
    åIJĥ
    0.09
    å¥ij约
    0.09
    å´´
    0.09
     Ton
    0.09
    å°ı说
    0.09
    éŀį
    0.09
    Activations Density 0.075%

    No Known Activations