© 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. 36702
    Prev
    Next
    INDEX
    Explanations

    treadmill exercise

    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
    æ¸İ
    -0.10
    åĹħ
    -0.08
    们
    -0.08
    们çļĦ
    -0.08
    æĥħ
    -0.08
    one
    -0.08
    adera
    -0.08
     móc
    -0.08
    çĹĽçĤ¹
    -0.08
    浪潮
    -0.08
    POSITIVE LOGITS
    tered
    0.10
    éĿŀåĩ¡
    0.09
    åıĹéĻIJ
    0.09
    èĢľ
    0.09
    èĮĦ
    0.09
    åī¿
    0.08
    èľļ
    0.08
    atables
    0.08
    éĹ²ç½®
    0.08
    å¸ĪèĮĥ
    0.08
    Activations Density 0.001%

    No Known Activations