© 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. 8924
    Prev
    Next
    INDEX
    Explanations

    campaigns and activism

    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
    éķĽ
    -0.09
     Skinner
    -0.09
     Joseph
    -0.08
    NOP
    -0.08
    棨
    -0.08
    çİĦ
    -0.08
    _PROTOCOL
    -0.08
    mö
    -0.08
    é£İåij³
    -0.08
    uum
    -0.08
    POSITIVE LOGITS
    ç»´æĿĥ
    0.17
     campaign
    0.13
    äºīåıĸ
    0.13
     campaigns
    0.12
    åĢ¡å¯¼
    0.12
     advocacy
    0.11
     Campaign
    0.11
     campaigners
    0.11
    çݯä¿Ŀ
    0.10
    åij¼åIJģ
    0.10
    Activations Density 0.176%

    No Known Activations