© 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. 4805
    Prev
    Next
    INDEX
    Explanations

    change becomes or turns into

    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
    ople
    -0.12
    eres
    -0.09
    çݳ
    -0.09
    urai
    -0.09
    å±ķå¼Ģ
    -0.08
    æľīè¿Ļæł·çļĦ
    -0.08
    侪
    -0.08
    ãĥķãĥªãĥ¼
    -0.08
    æĮ£
    -0.08
    atu
    -0.08
    POSITIVE LOGITS
    åıĺæĪIJäºĨ
    0.15
    åıĺæĪIJ
    0.13
    转åĮĸ为
    0.12
    åıĺ为
    0.12
    转åıĺ为
    0.12
    è®ĬæĪIJ
    0.10
    atron
    0.09
    å®ŀå®ŀåľ¨åľ¨
    0.09
     FOOT
    0.09
     اÙĦشر
    0.09
    Activations Density 0.065%

    No Known Activations