© 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. 48819
    Prev
    Next
    INDEX
    Explanations

    intensifier for 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
    lac
    -0.10
    manship
    -0.09
    çľĭä¼¼
    -0.09
    强大
    -0.08
    æĭīçĿĢ
    -0.08
    ä¿©
    -0.08
    éĺIJ
    -0.08
    å¯ĮåĬĽ
    -0.08
    ability
    -0.08
    èĮģ
    -0.08
    POSITIVE LOGITS
    oter
    0.11
    ÑĤеÑĢ
    0.10
    æĦıä¹īä¸ĬçļĦ
    0.10
    èķĪ
    0.09
    ulses
    0.09
    è¦ģ好好
    0.09
    åĩºäºİ
    0.09
    å±ŀå®ŀ
    0.09
    tes
    0.09
    HING
    0.09
    Activations Density 0.008%

    No Known Activations