© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6982
    Prev
    Next
    INDEX
    Explanations

    money paid or owed

    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
    itat
    -0.11
    ä¸Ĭè°ĥ
    -0.10
    åĩĢåĢ¼
    -0.09
    å¹²äºĭ
    -0.09
    çıŃ车
    -0.09
    éĿŀ常好
    -0.09
    åİŁæľīçļĦ
    -0.09
    ä½ĵçİ°åľ¨
    -0.09
    欣æħ°
    -0.09
    wert
    -0.09
    POSITIVE LOGITS
    era
    0.09
     kepada
    0.08
    æ¿
    0.08
    èĩ³
    0.08
    èij«èĬ¦
    0.08
    æĥħ
    0.08
    esto
    0.08
    ERA
    0.08
    æĹ¥èĩ³
    0.07
     Triple
    0.07
    Activations Density 0.025%

    No Known Activations