© 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. 20511
    Prev
    Next
    INDEX
    Explanations

    authors like Joyce and Mann

    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
    æĢĻ
    -0.10
    æ¼Ķ
    -0.09
    éĿ¢åŃIJ
    -0.09
    åĩıåħį
    -0.08
     vent
    -0.08
    å¼¼
    -0.08
    å¥ı
    -0.08
    alm
    -0.08
    æĦŁåĬ¨
    -0.08
    åħķ
    -0.07
    POSITIVE LOGITS
    ä¸Ń举
    0.10
    å¦ĵ
    0.10
    สรร
    0.10
    æııåĨĻ
    0.09
    çĪµå£«
    0.09
    诺è´Ŀå°Ķ
    0.09
    SSL
    0.09
     باÙĦÙĨ
    0.09
    .ssl
    0.09
    ä½ľåĵģåĨħ容
    0.09
    Activations Density 0.069%

    No Known Activations