© 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. 53195
    Prev
    Next
    INDEX
    Explanations

    X of Y quantitative phrases

    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
    zer
    -0.10
    æĹłè®ºå¦Ĥä½ķ
    -0.09
    swire
    -0.09
     Vox
    -0.09
    ä¸Ģ代
    -0.08
    åĬłåĢį
    -0.08
    ivals
    -0.08
     ÑĢеÑĪа
    -0.08
    çĻ¾å®¶
    -0.08
    èı©æıIJ
    -0.08
    POSITIVE LOGITS
    大大å°ıå°ı
    0.10
    åIJijå¤ĸ
    0.10
    åijĪ
    0.09
    å¾Ģå¤ĸ
    0.09
    éŀį
    0.09
    è¿ĻäºĽå¹´
    0.09
    渤
    0.09
    çļĦæĹ¥åŃIJéĩĮ
    0.09
    æĦıè§ģ建议
    0.09
    æ°¤
    0.09
    Activations Density 0.012%

    No Known Activations