© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5492
    Prev
    Next
    INDEX
    Explanations

    dust and erosion

    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
    è£ĺ
    -0.10
    ä¸įæĺİ
    -0.09
    .appspot
    -0.09
    hoe
    -0.09
    çľĦ
    -0.08
    .GetService
    -0.08
    åĬŁ
    -0.08
    åĵºä¹³
    -0.08
    overn
    -0.08
    zik
    -0.08
    POSITIVE LOGITS
     dust
    0.15
    æī¬å°ĺ
    0.13
    å°ĺ
    0.13
    塵
    0.12
    æĬĸ
    0.12
     Dust
    0.12
    ç²īå°ĺ
    0.12
    é£İåIJ¹
    0.10
    çģ°å°ĺ
    0.10
    ãģ¾ãģĦ
    0.09
    Activations Density 0.039%

    No Known Activations