© 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. 57991
    Prev
    Next
    INDEX
    Explanations

    saint and martyr figures

    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
    unger
    -0.09
    éħĿéħ¿
    -0.09
    corr
    -0.09
    áng
    -0.09
    红楼梦
    -0.08
    æ·±æĥħ
    -0.08
     rut
    -0.08
    æĥ´
    -0.08
    横åIJij
    -0.08
    åĸĿèĮ¶
    -0.08
    POSITIVE LOGITS
     martyr
    0.12
    æĬ¤
    0.10
     marty
    0.09
    æ®ī
    0.09
    äºĭ迹
    0.09
    å¢Ļå£ģ
    0.09
    éĻįæ°´
    0.08
    å¥ĩ迹
    0.08
    æīĵæĸŃ
    0.08
     Marty
    0.08
    Activations Density 0.075%

    No Known Activations