© 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. 63280
    Prev
    Next
    INDEX
    Explanations

    reduce consumption or emissions

    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
    好å¤Ħ
    -0.09
    çİij
    -0.09
    romise
    -0.09
    è¾ĥ好çļĦ
    -0.08
    ä¸ĬäºĨ
    -0.08
    èī¯å¥½çļĦ
    -0.08
    доб
    -0.08
     quo
    -0.08
    éĤ»å±ħ
    -0.08
    é£İåIJ¹
    -0.08
    POSITIVE LOGITS
    ä¸įå¿ħè¦ģçļĦ
    0.14
     overall
    0.12
    ä¾Ŀèµĸ
    0.11
    ä¸ĢåįĬ
    0.11
     reliance
    0.10
     dependence
    0.10
    æķ´ä½ĵ
    0.10
     hẳn
    0.10
    注åĨĮèµĦæľ¬
    0.10
    åĸ§
    0.10
    Activations Density 0.139%

    No Known Activations