© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31284
    Prev
    Next
    INDEX
    Explanations

    want, desire, urge

    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
    åIJĪçIJĨæĢ§
    -0.11
    太ä¹ħ
    -0.10
    太大
    -0.10
    ç¥ļ
    -0.09
    æıĨ
    -0.09
    æĩĭ
    -0.09
    æĬ¼
    -0.09
    å¾Ĺ太
    -0.09
    мел
    -0.09
    èĢĹ
    -0.09
    POSITIVE LOGITS
    æĥ³è¦ģ
    0.11
    欲
    0.11
    å¾Īæĥ³
    0.11
     desire
    0.10
     ÑħоÑĩ
    0.09
    onn
    0.09
    æĥ³åİ»
    0.09
     wanting
    0.09
    亲è¿ij
    0.09
    åĨ²åĬ¨
    0.09
    Activations Density 0.028%

    No Known Activations