© 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. 20359
    Prev
    Next
    INDEX
    Explanations

    political groups and constituents

    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
    ä½ľåĿĬ
    -0.10
    说åĩºæĿ¥
    -0.09
    åIJĦæł·
    -0.09
    åĥ»
    -0.09
    æ¹ĸåĮº
    -0.08
    çĶ·ä¸»
    -0.08
    产ä¸ļéĽĨ群
    -0.08
    èĻ½çĦ¶
    -0.08
    åĢ¦
    -0.08
     vign
    -0.08
    POSITIVE LOGITS
    ç¨Ģ
    0.09
    åıªéľĢ
    0.09
    æľ¬æĿ¥
    0.09
    æľīä»·åĢ¼
    0.09
    éģŃ
    0.09
     Continent
    0.08
    merce
    0.08
     aras
    0.08
    èIJĭ
    0.08
    çĮĿ
    0.08
    Activations Density 0.121%

    No Known Activations