© 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. 8246
    Prev
    Next
    INDEX
    Explanations

    one of 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
    é¼ĵ
    -0.10
    æݥ管
    -0.09
    æĸĻ
    -0.09
    æij¸
    -0.08
    è¿İåIJĪ
    -0.08
    rig
    -0.08
    hec
    -0.08
     ÑģпÑĢав
    -0.08
    &lt
    -0.08
    åIJĮæŶ
    -0.08
    POSITIVE LOGITS
    åİŁåĽłä¹ĭä¸Ģ
    0.16
    éĩįè¦ģåİŁåĽł
    0.11
    çļĦä¸Ģ项
    0.10
    çģŃ
    0.10
    éĩįè¦ģåĨħ容
    0.10
    çļĦéĩįè¦ģ
    0.10
    å¾Ī大çļĦ
    0.09
    æīĵå¾Ĺ
    0.09
     feature
    0.09
    大ãģįãģª
    0.09
    Activations Density 0.160%

    No Known Activations