© 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. 7294
    Prev
    Next
    INDEX
    Explanations

    USDA agricultural news

    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
    ä¼ļéķ¿
    -0.10
    izu
    -0.10
    åĪ¶éĢłä¸ļ
    -0.09
    èļĮ
    -0.08
    iers
    -0.08
    æľĪ亮
    -0.08
     hen
    -0.07
    åħļåı²
    -0.07
    å®ŀéĻħä¸Ĭ
    -0.07
    ãģ¨ãģĨ
    -0.07
    POSITIVE LOGITS
    贷款
    0.11
    髯
    0.10
    olie
    0.10
    à¸Ħา
    0.09
    æŃī
    0.09
    èł¹
    0.09
    æ£īèĬ±
    0.09
    oj
    0.09
    ä¸Ģç¬Ķ
    0.09
    oka
    0.09
    Activations Density 0.022%

    No Known Activations