© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37176
    Prev
    Next
    INDEX
    Explanations

    election or political race

    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
    åĺī
    -0.09
    à¦ĸ
    -0.09
    åĴ±
    -0.09
    åīįæıIJ
    -0.09
    maker
    -0.08
    稽
    -0.08
    å°Ĭ严
    -0.08
    ä¼İ
    -0.08
    ENCY
    -0.08
    åĮ¹
    -0.08
    POSITIVE LOGITS
    æĹ·
    0.10
    å·²ä¹ħçļĦ
    0.09
    çĽ¸ä¼ł
    0.09
    姣
    0.09
    ä¸ŃåŃĺåľ¨çļĦ
    0.09
    åľĪ
    0.08
    äºĭåħ³
    0.08
    à¸Ķวà¸ĩ
    0.08
    åıªåī©
    0.08
    legg
    0.08
    Activations Density 0.009%

    No Known Activations