© 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. 49229
    Prev
    Next
    INDEX
    Explanations

    have to + verb

    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
    ä¸Ģ项
    -0.09
    IRM
    -0.09
    AFX
    -0.09
    æľªèĥ½
    -0.08
    dataSource
    -0.08
    åıĪèĥ½
    -0.08
    ç»Ŀä¸į
    -0.08
    没èĥ½
    -0.08
    æĹłæĦı
    -0.08
    è¾¾ä¸įåĪ°
    -0.08
    POSITIVE LOGITS
    è¿Ļæł·æīįèĥ½
    0.12
    åģļçļĦäºĭæĥħ
    0.11
    åģļçļĦäºĭ
    0.10
    -have
    0.10
    说çļĦæĺ¯
    0.10
    -know
    0.09
    æĪijä»¬çŁ¥éģĵ
    0.09
    ered
    0.09
    ä¹Łåıªèĥ½
    0.09
    å¿įåıĹ
    0.09
    Activations Density 0.052%

    No Known Activations