© 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. 20698
    Prev
    Next
    INDEX
    Explanations

    -ster, -ard, -bek, -burg

    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
    èĩªåĪ¶
    -0.09
    _Handle
    -0.08
    å°Ĭ
    -0.08
    üstü
    -0.08
    rist
    -0.08
    弦
    -0.08
    å·¥å§Ķ
    -0.08
    æĬĴ
    -0.08
    encers
    -0.08
    çļĦå°±æĺ¯
    -0.08
    POSITIVE LOGITS
    _growth
    0.11
    owitz
    0.10
    ç»IJ
    0.09
    .mozilla
    0.09
    ovich
    0.09
    ç¼ĸç¨ĭ
    0.08
    å°ģéĶģ
    0.08
    èĩ¬
    0.08
    AMS
    0.08
    åįľ
    0.08
    Activations Density 0.367%

    No Known Activations