© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 7735
    Prev
    Next
    INDEX
    Explanations

    with the

    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
    lichkeit
    -0.11
    人人
    -0.11
    人人éĥ½
    -0.11
    åĩ¡æĺ¯
    -0.10
    åĢĺ
    -0.09
    orer
    -0.09
    æīĵåĩº
    -0.09
    大èĤ¡ä¸ľ
    -0.09
    oter
    -0.09
    çĿ¦
    -0.09
    POSITIVE LOGITS
     ÙĤض
    0.10
    zens
    0.09
    çĮ¿
    0.08
    è¿Ļåľº
    0.08
    зи
    0.08
    ÙĤض
    0.08
    ses
    0.08
    å¾Īå¤ļäºĭæĥħ
    0.08
     regarding
    0.08
    åύåħ·
    0.08
    Activations Density 0.043%

    No Known Activations