© 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. 9284
    Prev
    Next
    INDEX
    Explanations

    companies and brands

    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
    åĵģ
    -0.10
    ingly
    -0.09
    åĮºåĨħ
    -0.09
    俱
    -0.09
    ä¸Ģ个éĩįè¦ģ
    -0.08
    emente
    -0.08
    ä»İä¸ļ
    -0.08
     невоз
    -0.08
    Demo
    -0.08
    demo
    -0.08
    POSITIVE LOGITS
    ä½İ端
    0.10
    oin
    0.09
    çļĦèĢģ
    0.09
    orta
    0.09
     Bain
    0.09
     UNITY
    0.08
    åIJĪä½ľåħ³ç³»
    0.08
    å§ĵ
    0.08
    ä¸Ģåij³
    0.08
    _Native
    0.08
    Activations Density 0.050%

    No Known Activations