© 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. 52300
    Prev
    Next
    INDEX
    Explanations

    mattress and beds

    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
    åĭ¾
    -0.10
    佩æľį
    -0.10
    æĤ£ä¸Ĭ
    -0.09
    èĪĮ头
    -0.09
    追究
    -0.09
    æµģåŁŁ
    -0.09
    è¡Įäºĭ
    -0.09
     Glasses
    -0.09
    触åıĬ
    -0.09
    éĴ³
    -0.09
    POSITIVE LOGITS
    åºĬåŀ«
    0.16
    åºĬ
    0.14
    æ²Ļåıij
    0.14
    åºĬä¸Ĭ
    0.13
    榻
    0.12
     mattress
    0.12
    æ²Ļåıijä¸Ĭ
    0.11
    å¯Ŀ
    0.11
    çī
    0.11
     beds
    0.11
    Activations Density 0.111%

    No Known Activations