© 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. 36179
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by verbs/adjectives

    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¸įä»ħèĥ½
    -0.12
    ä¸įä»ħåı¯ä»¥
    -0.11
    çļĦæĥħ绪
    -0.10
    åı¯ä»¥å¸®åĬ©
    -0.10
    ç¿Į
    -0.10
    çļĦéĩįè¦ģæĢ§
    -0.10
    èĥ½æ»¡è¶³
    -0.10
    vie
    -0.09
    çļĦéŃħåĬĽ
    -0.09
    çļĦæķĻåѦ
    -0.09
    POSITIVE LOGITS
    ä¹ŁåIJĮæł·
    0.09
    æĪļ
    0.09
    ä¸ĭå·´
    0.09
    ä¹Łæĺ¯å¦ĤæѤ
    0.08
    éķ¿å®ī
    0.08
    hausen
    0.08
    strom
    0.08
    -BEGIN
    0.08
    åĵ¥
    0.08
    å°±æĺ¯è¿Ļæł·
    0.08
    Activations Density 0.735%

    No Known Activations