© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20890
    Prev
    Next
    INDEX
    Explanations

    time remaining or countdowns

    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
    æľīèī²
    -0.09
    (simp
    -0.09
     Evening
    -0.09
     Moor
    -0.08
    Higher
    -0.08
     Rug
    -0.08
    éĺī
    -0.08
     Bail
    -0.08
    éªĮ
    -0.08
    æķŀå¼Ģ
    -0.08
    POSITIVE LOGITS
     countdown
    0.19
    åĢĴ
    0.15
     Countdown
    0.13
    åī©ä½Ļ
    0.13
    æĹ¥åŃIJ
    0.12
     remaining
    0.11
    åī©ä¸ĭçļĦ
    0.11
    åıªåī©ä¸ĭ
    0.11
    åī©
    0.11
    .remaining
    0.11
    Activations Density 0.062%

    No Known Activations