© 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. 20575
    Prev
    Next
    INDEX
    Explanations

    codes and abbreviations

    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
    å®Ĺ
    -0.09
    à¤Ŀ
    -0.09
    éľŃ
    -0.09
    ACES
    -0.09
    .Te
    -0.08
    etur
    -0.08
    ä¸į顾
    -0.08
    åĶ
    -0.08
    ACHE
    -0.08
    ately
    -0.08
    POSITIVE LOGITS
    avelength
    0.12
    ding
    0.11
    shops
    0.10
    ORLD
    0.10
    ä¸ĢåĪ»
    0.10
    old
    0.10
    esome
    0.10
    æݧèĤ¡éĽĨåĽ¢
    0.09
    æĢĢæĬ±
    0.09
    front
    0.09
    Activations Density 0.112%

    No Known Activations