© 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. 8163
    Prev
    Next
    INDEX
    Explanations

    via

    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
    è¯Ŀ说
    -0.10
    éĥ¢
    -0.10
    rew
    -0.09
    колÑĮ
    -0.09
     Wenger
    -0.09
    ervo
    -0.09
    屿
    -0.09
    uitive
    -0.08
    å°ıçĭĹ
    -0.08
     Spears
    -0.08
    POSITIVE LOGITS
    iso
    0.09
    èĩªçĦ¶èĢĮ
    0.09
    ä¸Ģéģį
    0.08
    ä½ķå¤Ħ
    0.08
    è¿Ļåıª
    0.08
    ä¸Ģ次次
    0.08
     Tender
    0.08
    eur
    0.08
    hap
    0.08
    è¡·å¿ĥ
    0.08
    Activations Density 0.053%

    No Known Activations