© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9802
    Prev
    Next
    INDEX
    Explanations

    what's going on

    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
    æ±°
    -0.10
    ä¸Ģ举
    -0.10
    ä¸Ģçľ¼
    -0.09
    èIJ½åĪ°
    -0.09
    çļĦ好å¤Ħ
    -0.09
    umes
    -0.09
    tons
    -0.09
    ä¸ĢçĤ¹åĦ¿
    -0.08
    ä¸Ģæł·
    -0.08
    è§ģåĪ°
    -0.08
    POSITIVE LOGITS
    æŃ¤äºº
    0.10
    å±ĢåĬ¿
    0.09
    ä¸įåģľçļĦ
    0.09
    æĿĤ
    0.09
    odo
    0.08
    _BP
    0.08
    ä¸įæĸŃçļĦ
    0.08
    é¼į
    0.08
    åİŁä»¶
    0.08
    åħ®
    0.08
    Activations Density 0.013%

    No Known Activations