© 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. 9720
    Prev
    Next
    INDEX
    Explanations

    draws and attracts

    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®¤çľŁèIJ½å®ŀ
    -0.09
    enheim
    -0.09
    è¿ĻçĤ¹
    -0.09
    èİ·å¾ĹæĽ´å¤ļ
    -0.08
    è®©æĽ´å¤ļ
    -0.08
    å§ĭç»Īä¿ĿæĮģ
    -0.08
    .IsEnabled
    -0.08
    onica
    -0.08
    çĶŁçĶŁ
    -0.08
     diam
    -0.08
    POSITIVE LOGITS
     tá»·
    0.10
    èĥľä»»
    0.09
    ä¸ĢæŶ
    0.09
    ä½ıäºĨ
    0.09
    åħ¥ä½ı
    0.09
    çľ¼çIJĥ
    0.09
    泪水
    0.08
    ä¼łåªĴ
    0.08
    åIJĦåľ°
    0.08
    ling
    0.08
    Activations Density 0.011%

    No Known Activations