© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52530
    Prev
    Next
    INDEX
    Explanations

    go to

    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
    anye
    -0.09
    åĪ¶
    -0.09
    é¹Ħ
    -0.09
    åľ¨åIJĮä¸Ģ
    -0.09
    ä¸Ģäºĭ
    -0.09
    ellen
    -0.09
    åIJijåīį
    -0.09
    代
    -0.09
    mal
    -0.09
    èµ°åIJij
    -0.09
    POSITIVE LOGITS
    è¹Ħ
    0.10
    æīįèĥ½å¤Ł
    0.10
    éĥ½è§īå¾Ĺ
    0.09
    äºĨå¾Īå¤ļ
    0.09
    æīįåı¯ä»¥
    0.09
    ioned
    0.09
    æݧèĤ¡éĽĨåĽ¢
    0.08
    æīįèĥ½
    0.08
    timeofday
    0.08
    ingleton
    0.08
    Activations Density 0.025%

    No Known Activations