© 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. 37164
    Prev
    Next
    INDEX
    Explanations

    great / amazing + noun

    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
    ä»Ģä¹Īåij¢
    -0.09
     wohl
    -0.09
    åģ·
    -0.08
    éĶĢåĶ®äººåijĺ
    -0.08
    诸
    -0.08
    pad
    -0.08
    æĺ¯ä»Ģä¹Īåij¢
    -0.08
    anye
    -0.08
     Arn
    -0.08
    _ANY
    -0.08
    POSITIVE LOGITS
    ãģĹãģķ
    0.10
    éĩįè¦ģåĨħ容
    0.09
    æľīä»·åĢ¼
    0.09
    并åIJij
    0.09
    erd
    0.09
    çŃĸ
    0.08
    _mD
    0.08
    éĵ§
    0.08
    ness
    0.08
     Content
    0.08
    Activations Density 0.013%

    No Known Activations