© 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. 8852
    Prev
    Next
    INDEX
    Explanations

    first idea or attempt

    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
    没æľī人
    -0.11
    ucky
    -0.09
    /cop
    -0.09
    åİ»çľĭ
    -0.09
    没人
    -0.09
    è¾ľ
    -0.08
    callbacks
    -0.08
    æĽ´å¥½åľ°
    -0.08
    åģıè¿ľ
    -0.08
    æĪijçľĭ
    -0.08
    POSITIVE LOGITS
    å¸ĮæľĽéĢļè¿ĩ
    0.09
    herit
    0.09
    æݥ触
    0.09
     concern
    0.09
    ä¾Ŀæīĺ
    0.09
    æĦŁåıĹåĪ°äºĨ
    0.09
    æĭĬ
    0.09
     contact
    0.08
    ride
    0.08
    宣
    0.08
    Activations Density 0.035%

    No Known Activations