© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 17
    Prev
    Next
    INDEX
    Explanations

    election campaign funding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    broken
    -0.24
    æijŀ
    -0.24
     incom
    -0.23
    æ¡´
    -0.23
     wrink
    -0.23
     наÑĢ
    -0.23
    楮
    -0.23
     navigator
    -0.23
    inear
    -0.23
     Budd
    -0.22
    POSITIVE LOGITS
     voter
    0.34
     elections
    0.32
    æĶ¿æ²»
    0.31
     Elections
    0.31
    å®ļåIJij
    0.29
     campaigns
    0.29
     funded
    0.29
    -funded
    0.29
    Campaign
    0.28
    ç«ŀéĢī
    0.28
    Activations Density 0.018%

    No Known Activations