© 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. 19839
    Prev
    Next
    INDEX
    Explanations

    smoothness

    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
    åĩ»
    -0.10
    åIJĮçŃī
    -0.10
    rog
    -0.09
    æ¯ģ
    -0.09
    åıĤåĬłä¼ļè®®
    -0.09
    éĹ»
    -0.09
    éŀij
    -0.09
    aho
    -0.09
    ä¸įå¾Ĺå·²
    -0.09
    诱
    -0.09
    POSITIVE LOGITS
    顺åĪ©
    0.21
    顺çķħ
    0.20
     smooth
    0.18
    smooth
    0.17
    æµģçķħ
    0.16
     smoothly
    0.16
     Smooth
    0.16
    Smooth
    0.15
     smoother
    0.14
    平稳
    0.14
    Activations Density 0.075%

    No Known Activations