© 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. 51909
    Prev
    Next
    INDEX
    Explanations

    science concepts

    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
    ktop
    -0.09
    èīº
    -0.09
    æķ£æĪ·
    -0.09
    AMPLE
    -0.09
    uper
    -0.09
    åĶ±æŃĮ
    -0.09
    upro
    -0.09
    æĿ¼
    -0.09
    .ErrorCode
    -0.09
    éŀį
    -0.08
    POSITIVE LOGITS
    æݢ究
    0.10
    笥
    0.10
    ç§ijåѦçłĶ究
    0.09
    cts
    0.09
    å®ŀéªĮ
    0.09
    æ»ĵ
    0.09
    çŃ¾
    0.09
    箧
    0.08
     Cru
    0.08
     Scientist
    0.08
    Activations Density 0.050%

    No Known Activations