© 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. 36481
    Prev
    Next
    INDEX
    Explanations

    smoke and exhaust pollutants

    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
    axy
    -0.10
    kim
    -0.09
    丰æĶ¶
    -0.09
    .dispatchEvent
    -0.09
    éĹ°
    -0.08
    åıĪæĺ¯
    -0.08
    aml
    -0.08
     derog
    -0.08
    ám
    -0.08
    çݯä¿Ŀ
    -0.08
    POSITIVE LOGITS
    ê°Ŀ
    0.09
    ç¼Ń
    0.09
    imas
    0.09
    Traversal
    0.09
    è¡Į人
    0.08
     passing
    0.08
     اÙĦØŃÙĤÙĪÙĤ
    0.08
    Daniel
    0.08
    eri
    0.08
    _PARTITION
    0.08
    Activations Density 0.053%

    No Known Activations