© 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. 9615
    Prev
    Next
    INDEX
    Explanations

    fatty acids and omega types

    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
    _MO
    -0.09
    å¹³
    -0.09
    å¹³éĿ¢
    -0.09
    nova
    -0.09
    riott
    -0.09
    念
    -0.08
     оÑĩеÑĢед
    -0.08
     Taj
    -0.08
    ılı
    -0.08
    odia
    -0.08
    POSITIVE LOGITS
    å¿ħéľĢ
    0.12
    ç¨Ģ缺
    0.10
    ä¸įåı¯æĪĸ缺
    0.10
    å¿ħä¸įåı¯å°ij
    0.10
     essential
    0.10
    æħij
    0.09
    åĩ¶
    0.09
    身价
    0.09
    紧缺
    0.09
    udu
    0.09
    Activations Density 0.113%

    No Known Activations