© 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. 62281
    Prev
    Next
    INDEX
    Explanations

    critical thinking and higher order

    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
    ç»į
    -0.09
    ä¼łæİĪ
    -0.09
    åŃļ
    -0.08
    èµĢ
    -0.08
    reen
    -0.08
    ween
    -0.08
    ä½ĵ积
    -0.08
    çłĶ究æĪIJæŀľ
    -0.08
    å£ģ
    -0.08
    artner
    -0.08
    POSITIVE LOGITS
    æĢĿç»´
    0.24
    æĢĿèĢĥ
    0.20
    æĢĿç»´æĸ¹å¼ı
    0.19
    éĢ»è¾ij
    0.18
     thinking
    0.18
    æݨçIJĨ
    0.17
    thinking
    0.16
     logic
    0.16
    æĢĿ
    0.15
     reasoning
    0.15
    Activations Density 0.042%

    No Known Activations