© 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. 57350
    Prev
    Next
    INDEX
    Explanations

    being 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
    .cz
    -0.10
    满æĦıçļĦ
    -0.09
    é¼ĵ
    -0.09
    uco
    -0.08
     samt
    -0.08
    çłĶ究ä¸Ńå¿ĥ
    -0.08
    å¾ģ
    -0.08
    éĴ°
    -0.08
    çģŃ
    -0.08
    è¦ģ害
    -0.08
    POSITIVE LOGITS
    åĮħ容
    0.12
    å¼ĢéŨ
    0.10
    宽容
    0.09
    åĬ¡å®ŀ
    0.09
    éħİ
    0.09
    æħ·æħ¨
    0.09
    ç«ĭåľº
    0.09
    ãģ¤ãģĭ
    0.09
    æŁĶåĴĮ
    0.08
    åīįçŀ»æĢ§
    0.08
    Activations Density 0.199%

    No Known Activations