© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35649
    Prev
    Next
    INDEX
    Explanations

    political agenda and bias

    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
    ä¼Ĺ
    -0.10
    acer
    -0.09
     Tough
    -0.09
    è¿·
    -0.08
    heid
    -0.08
     Bek
    -0.08
    adio
    -0.08
    ç²¾é«ĵ
    -0.08
     Nail
    -0.08
    åı±
    -0.08
    POSITIVE LOGITS
    ç«ĭåľº
    0.11
     agendas
    0.11
    agenda
    0.10
    缮çļĦ
    0.10
     agenda
    0.10
    çĭŃ
    0.10
    主è§Ĥ
    0.10
    ä¸Ģè´¯
    0.10
    åģı
    0.09
    æĶ»åĬ¿
    0.09
    Activations Density 0.096%

    No Known Activations