© 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. 33537
    Prev
    Next
    INDEX
    Explanations

    professor of English

    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
    adel
    -0.09
    æķĹ
    -0.09
    çļĦåīįæıIJ
    -0.08
    骨骼
    -0.08
    çĶ·å¥³
    -0.08
    lus
    -0.08
    chant
    -0.08
    ä¸Ń央空è°ĥ
    -0.08
    isti
    -0.08
    _VOL
    -0.08
    POSITIVE LOGITS
    ç³»
    0.09
    oulder
    0.09
    é¾Ļ头
    0.09
    ä¸Ī
    0.09
    ail
    0.08
    人工
    0.08
    ëĭ¤ê°Ģ
    0.08
    éĢ¸
    0.08
    éħŀ
    0.08
    çĨĬ
    0.08
    Activations Density 0.057%

    No Known Activations