© 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. 20635
    Prev
    Next
    INDEX
    Explanations

    honeycomb structure or panels

    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
    ç¾ĬèĤī
    -0.09
     firm
    -0.09
     Firm
    -0.09
    eline
    -0.08
    aroo
    -0.08
    èįī
    -0.08
    ion
    -0.08
    ively
    -0.08
    firm
    -0.08
    åijĺ
    -0.08
    POSITIVE LOGITS
    ago
    0.10
    èĹ¿
    0.09
    èººåľ¨åºĬä¸Ĭ
    0.08
    å¯ĩ
    0.08
    ugal
    0.08
    çķ¿
    0.08
    åįļ主
    0.08
    æĭĻ
    0.08
    ä½ĵè´´
    0.08
    Ø·ÙĬب
    0.08
    Activations Density 0.002%

    No Known Activations