© 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. 37428
    Prev
    Next
    INDEX
    Explanations

    Labour politicians and politics

    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
    èİŀ
    -0.08
    褥
    -0.08
    主åĬ¨æĢ§
    -0.08
    çIJĨæĻº
    -0.08
    sti
    -0.08
     COPYRIGHT
    -0.08
    çĻ½é©¬
    -0.08
    ego
    -0.08
     extr
    -0.07
    _holder
    -0.07
    POSITIVE LOGITS
    udi
    0.09
    town
    0.09
    odyn
    0.09
    ä¸įçķĻ
    0.09
    ritch
    0.09
    åĴ«
    0.09
    æĬij
    0.09
    å½ĵä¹ĭ
    0.09
     ÑĦоÑĢ
    0.09
    oney
    0.08
    Activations Density 0.004%

    No Known Activations