© 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. 2777
    Prev
    Next
    INDEX
    Explanations

    political campaigns and elections

    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
    irt
    -0.10
    æĸij
    -0.09
    hunt
    -0.09
    éĢı
    -0.09
    æ¼ī
    -0.08
    ãģĭãĤĬ
    -0.08
    俵
    -0.08
    Toolkit
    -0.08
    ernal
    -0.08
    æĮīæŶ
    -0.08
    POSITIVE LOGITS
    è¿Ľåıĸ
    0.10
    åĨ²åĩ»
    0.10
    ä»£æĽ¿
    0.10
     ÑĥÑĩаÑģÑĤие
    0.10
    å¤©çľŁ
    0.10
    è¿ľæ´ĭ
    0.10
    çŁ¥åIJį度
    0.09
    京åŁİ
    0.09
    åĽ¢ä½ĵ
    0.09
    é¹ĥ
    0.09
    Activations Density 0.082%

    No Known Activations