© 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. 7512
    Prev
    Next
    INDEX
    Explanations

    hypothetical outcomes

    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
    elp
    -0.09
    ileo
    -0.09
    æĬ¤
    -0.08
    å¹Į
    -0.08
    éĤ£éĩĮ
    -0.08
    åįĩ
    -0.08
    enburg
    -0.08
     haz
    -0.08
    æľīæĿ¡ä»¶
    -0.08
    åħ°
    -0.08
    POSITIVE LOGITS
    ä¼ļ让
    0.10
    æĪij们ä¼ļ
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.09
     Ø¥ØŃ
    0.09
    åıĮèµ¢
    0.09
    íijľ
    0.09
    çļĦè¯Ŀ
    0.09
    ypical
    0.09
    ocha
    0.09
     Wich
    0.09
    Activations Density 0.059%

    No Known Activations