© 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. 49523
    Prev
    Next
    INDEX
    Explanations

    election campaign activities

    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
    梯
    -0.09
    burgh
    -0.09
    åħ®
    -0.09
    羣æĥħ
    -0.09
    产æĿĥ
    -0.09
    å·´æĭī
    -0.09
    主ä¹īèĢħ
    -0.09
    alties
    -0.09
    çľ¼éĩĮ
    -0.09
    én
    -0.09
    POSITIVE LOGITS
    วล
    0.09
    sWith
    0.08
    æĪijåİ»
    0.08
    .ws
    0.08
    æľŁéĹ´
    0.08
    ç§ijåѦåıijå±ķ
    0.08
     Pell
    0.08
    纪
    0.07
    ä¸Ńä¿Ħ
    0.07
    ista
    0.07
    Activations Density 0.012%

    No Known Activations