© 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. 20649
    Prev
    Next
    INDEX
    Explanations

    climate change and policy

    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
    说æľį
    -0.09
    esch
    -0.09
    ras
    -0.09
    æĸ°æĹ¶æľŁ
    -0.09
    们
    -0.09
    çIJĨçĶ±
    -0.09
    ยà¸ģ
    -0.09
    .tk
    -0.09
    楣
    -0.09
    _Adjust
    -0.08
    POSITIVE LOGITS
    大åĨĽ
    0.09
    åŃ¦å®¶
    0.09
    bero
    0.09
    çĤİçĥŃ
    0.08
     sobie
    0.08
    /weather
    0.08
    bul
    0.08
    /ec
    0.08
    ем
    0.08
    éľ¾
    0.08
    Activations Density 0.012%

    No Known Activations