© 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. 37559
    Prev
    Next
    INDEX
    Explanations

    legal sections and rules

    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
    åıĪ好
    -0.10
    kap
    -0.08
    .sl
    -0.08
    大约
    -0.08
    åºĦ
    -0.08
    cil
    -0.08
    Submitted
    -0.08
    krit
    -0.08
    zens
    -0.07
    ä¹Ŀ大
    -0.07
    POSITIVE LOGITS
    åı¦æľī
    0.10
    ç§ĺå¯Ĩ
    0.09
    家åĸ»æĪ·æĻĵ
    0.09
    æ¹®
    0.08
     elsewhere
    0.08
     ×Ļ×Ķ×Ļ×Ķ
    0.08
    è¿Ļ个ä¸ĸçķĮ
    0.08
    ediator
    0.08
     latter
    0.08
    enga
    0.08
    Activations Density 0.046%

    No Known Activations