© 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. 7884
    Prev
    Next
    INDEX
    Explanations

    wearable accessories and suits

    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
    弯
    -0.10
    éľī
    -0.10
    çŃ¾
    -0.09
    é¾ĭ
    -0.09
    ä¹Ĵ
    -0.09
    åįģä½Ļå¹´
    -0.09
    ä½į
    -0.09
    æ£
    -0.09
    车ä½į
    -0.09
    路线
    -0.09
    POSITIVE LOGITS
    身ä¸Ĭ
    0.11
    æĪ´
    0.11
    ä¸Ģ身
    0.11
    ä¸ĢèĤ¡
    0.09
    å¥Ĺè£ħ
    0.09
    çķľ
    0.09
    佩æĪ´
    0.09
    åĬ©
    0.09
    骨骼
    0.08
    åİļåİļçļĦ
    0.08
    Activations Density 0.160%

    No Known Activations