© 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. 23867
    Prev
    Next
    INDEX
    Explanations

    place names ending in ley, wich, land, pool, head, nes, on, bury

    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
    æī¶
    -0.11
    toi
    -0.09
    ä¸ĸ人
    -0.09
     Charleston
    -0.09
    .ls
    -0.09
    ä¸ĸçķĮ第ä¸Ģ
    -0.09
    æµħ
    -0.09
    åįŀ
    -0.08
    æĺ¯éŁ©åĽ½
    -0.08
    åĽĽå·Ŀçľģ
    -0.08
    POSITIVE LOGITS
    pler
    0.11
    maal
    0.10
     Leeds
    0.10
    å®ģ
    0.09
    RAR
    0.09
    æĽ¼èģĶ
    0.09
     tar
    0.09
     Arab
    0.09
    RAP
    0.09
    INDER
    0.09
    Activations Density 0.147%

    No Known Activations