© 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. 37178
    Prev
    Next
    INDEX
    Explanations

    elected member of parliament or constituency

    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
    æĶ¶èİ·
    -0.11
    åĵı
    -0.10
    å±Ĥåĩº
    -0.10
    دÙĬÙĨ
    -0.10
    æŀ¶æŀĦ
    -0.10
    åħ¨å±Ģ
    -0.10
    åIJĪä½ľåħ±èµ¢
    -0.10
    æµĩæ°´
    -0.09
    æµĩ
    -0.09
    æ°ijæĹıæĸĩåĮĸ
    -0.09
    POSITIVE LOGITS
    æĵ¦
    0.10
     nad
    0.08
    eve
    0.08
    .Lang
    0.08
    åİ¿å§Ķ书记
    0.08
     precinct
    0.08
    åİĤæĪ¿
    0.08
     NOI
    0.08
    tape
    0.07
     Robbins
    0.07
    Activations Density 0.264%

    No Known Activations