© 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. 35315
    Prev
    Next
    INDEX
    Explanations

    links to

    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
    æıĨ
    -0.10
    è¯Ī
    -0.10
    å¾Ģä¸ĭ
    -0.09
    æ¦Ĩ
    -0.09
    åįķ纯çļĦ
    -0.09
    äºĮ人
    -0.09
    éĺħ读åħ¨æĸĩ
    -0.09
    åĬ¨äºº
    -0.09
    两个人
    -0.09
    åĭī强
    -0.09
    POSITIVE LOGITS
    é¾Ł
    0.10
    airo
    0.09
     sunday
    0.08
    äºĶæĺŁ
    0.08
    声
    0.08
    esson
    0.08
     cropped
    0.08
    iset
    0.08
    ourt
    0.08
    NING
    0.08
    Activations Density 0.037%

    No Known Activations