© 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. 23265
    Prev
    Next
    INDEX
    Explanations

    adverbs followed by nouns or 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¸įæŃ»
    -0.09
    ç¿ķ
    -0.08
    å¼ĢèįĴ
    -0.08
    è¿Ļç¯ĩ
    -0.08
    è¿ĶåĽŀ
    -0.08
    é¢ģ
    -0.08
    èĩªåıij
    -0.08
    æ´¼
    -0.08
    çĮĸ
    -0.08
     صÙģ
    -0.08
    POSITIVE LOGITS
    çĶļ
    0.10
    å±IJ
    0.10
    reads
    0.09
    åijĪçİ°
    0.09
    ä»Ģä¹Īæł·
    0.08
    说çļĦè¯Ŀ
    0.08
    onas
    0.08
    åºŁè¯Ŀ
    0.08
    BITS
    0.08
    æĦıæĢĿ
    0.08
    Activations Density 0.186%

    No Known Activations