© 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. 20944
    Prev
    Next
    INDEX
    Explanations

    dew, wet, spray, cling

    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
    æĮĸ
    -0.10
    æIJŃæ¡£
    -0.09
    mas
    -0.09
    ç»ŀ
    -0.08
    æīĶ
    -0.08
    åŁĭ
    -0.08
    æıĴåħ¥
    -0.08
    常年
    -0.08
    éĶ¢
    -0.08
    å¹´èĩ³
    -0.08
    POSITIVE LOGITS
    éľľ
    0.13
    ä¸Ģå¤ľ
    0.13
     dew
    0.12
     Dew
    0.11
    æĻ¨
    0.10
     morning
    0.10
    æĹ©æĻ¨
    0.09
     Overnight
    0.09
    æ²¾
    0.09
    æĹ©ä¸Ĭ
    0.09
    Activations Density 0.027%

    No Known Activations