© 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. 55226
    Prev
    Next
    INDEX
    Explanations

    Chinese medicine and acupuncture

    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
    åłµ
    -0.10
    .lists
    -0.09
    gMaps
    -0.09
    éĻŁ
    -0.09
    ÑĢай
    -0.09
    åĿĤ
    -0.08
    å§Ĺ
    -0.08
    THON
    -0.08
    asz
    -0.08
    ä¸ĵé¢ĺ
    -0.08
    POSITIVE LOGITS
    é«Ń
    0.10
    ç¨Ĺ
    0.09
    æĦį
    0.09
    é»ijé¾Ļ
    0.08
    大çģ«
    0.08
    endar
    0.08
    çĥŃ带
    0.08
    ç»įåħ´
    0.08
    -line
    0.08
    oref
    0.08
    Activations Density 0.024%

    No Known Activations