© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36988
    Prev
    Next
    INDEX
    Explanations

    for every member

    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
    å®
    -0.09
    æľīçļĦ
    -0.08
    åIJĦ项
    -0.08
     tut
    -0.08
    æį¢
    -0.08
    å¾Īåĸľæ¬¢
    -0.08
    ä¸įçĶ¨æĭħå¿ĥ
    -0.07
    大家åı¯ä»¥
    -0.07
    ç¦Ħ
    -0.07
    举åĬŀäºĨ
    -0.07
    POSITIVE LOGITS
    åıªè¦ģæĺ¯
    0.10
    ç¡ĸ
    0.10
    éĥ½åºĶ该
    0.10
    æĤ¦
    0.10
    äºĨ解
    0.10
    Toolkit
    0.10
     lắp
    0.09
    åĵªæĢķ
    0.09
    ä½ĵè´´
    0.09
     bestellen
    0.09
    Activations Density 0.049%

    No Known Activations