© 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. 36785
    Prev
    Next
    INDEX
    Explanations

    time taken or speed

    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
    éĢĤæŶ
    -0.10
    kick
    -0.10
    俸
    -0.10
    èħIJ
    -0.09
    åĩºæ¸¸
    -0.09
    祸
    -0.09
    ä¸Ģ个æĺŁæľŁ
    -0.09
    忧
    -0.09
     timetable
    -0.08
    纯æ´ģ
    -0.08
    POSITIVE LOGITS
    éĢŁåº¦
    0.11
    äºĶåĪĨéĴŁ
    0.10
    åĮĨåĮĨ
    0.10
    çļĦéĢŁåº¦
    0.10
    åįĬ个å°ıæŶ
    0.09
    åįģåĪĨéĴŁ
    0.09
    æħ¢
    0.09
     Minute
    0.09
    åįĪ
    0.09
     finish
    0.08
    Activations Density 0.107%

    No Known Activations