© 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. 35225
    Prev
    Next
    INDEX
    Explanations

    quite followed by adjective

    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
    æĥħæĦŁ
    -0.10
    æŀģåħ¶
    -0.09
    vel
    -0.09
    atically
    -0.08
     пÑĥ
    -0.08
     ÑħоÑĤÑĮ
    -0.08
    ÑĪка
    -0.08
    å¿ĥ头
    -0.08
    æĺĻ
    -0.08
    责任æĦŁ
    -0.08
    POSITIVE LOGITS
    ä¸įéĶĻçļĦ
    0.11
    å½ĵä¹ĭ
    0.10
     обеÑģп
    0.10
    /ext
    0.09
    çļĦä¸ĢéĿ¢
    0.09
    /random
    0.09
    añ
    0.09
    ãģªãĤĤãģ®
    0.09
    .onStart
    0.09
    äºĨä¸įå°ij
    0.09
    Activations Density 0.017%

    No Known Activations