© 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. 4605
    Prev
    Next
    INDEX
    Explanations

    political discourse

    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
    ä½ĵè´¨
    -0.11
    欢
    -0.10
    缦
    -0.10
    دا
    -0.09
    åĪ¨
    -0.09
    ä¸ĢæĹ¥
    -0.09
    èĪį
    -0.09
    é¢ĩ
    -0.09
    æĹģ
    -0.09
    çĽ¸å¹²
    -0.09
    POSITIVE LOGITS
     crow
    0.09
     lap
    0.08
     Mess
    0.08
    latin
    0.08
    ä¸ŃåĽ½çĶµä¿¡
    0.08
    ä¸ŃåĽ½ç»ıæµİ
    0.08
    æĢ¿
    0.08
    anson
    0.08
    è¿ŀ线
    0.07
     wing
    0.07
    Activations Density 0.141%

    No Known Activations