© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33380
    Prev
    Next
    INDEX
    Explanations

    political rallies and campaigns

    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
    ä»ĭ
    -0.09
    ÙĦÙĬÙĨ
    -0.09
     playable
    -0.09
    zas
    -0.09
    ä½ĵçİ°åĩº
    -0.09
    extracomment
    -0.09
    æ¡£æ¡Ī
    -0.08
    éĶĻäºĨ
    -0.08
    èĭĴ
    -0.08
    aths
    -0.08
    POSITIVE LOGITS
    群ä¼Ĺ
    0.10
    à¸Ľà¸£à¸²
    0.10
    ICON
    0.09
     crowds
    0.09
    çĺ¿
    0.09
    大ä¼ļ
    0.08
    广大群ä¼Ĺ
    0.08
     Mega
    0.08
    ç¨į
    0.08
    åħ¥åºĵ
    0.08
    Activations Density 0.150%

    No Known Activations