© 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. 37834
    Prev
    Next
    INDEX
    Explanations

    way to enjoy, make, get

    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¿Ļæł·ä¸Ģ
    -0.10
    åı²ä¸ĬæľĢ
    -0.09
     somehow
    -0.09
    ille
    -0.09
    å¼ĥ
    -0.09
    dale
    -0.08
    æĺŁè¾°
    -0.08
    äºĨäºĽ
    -0.08
    ä¹ľ
    -0.08
    spl
    -0.08
    POSITIVE LOGITS
     otherwise
    0.10
     oneself
    0.10
     yourself
    0.10
    ä¸įçĦ¶
    0.09
    èİ·å¾Ĺ
    0.09
    èİ·å¾ĹæĦŁ
    0.09
    ÑĥÑĩа
    0.09
    ä¸į对
    0.08
    æ´»çĿĢ
    0.08
    çļĦæĸ¹å¼ı
    0.08
    Activations Density 0.298%

    No Known Activations