© 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. 53887
    Prev
    Next
    INDEX
    Explanations

    dance companies and ballet

    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
    .sdk
    -0.10
    .Sdk
    -0.10
    è¿Ļ家ä¼Ļ
    -0.09
    ائÙĨ
    -0.09
    éĴĵé±¼
    -0.09
    çIJIJ
    -0.09
    Speaker
    -0.09
     coun
    -0.09
    æł¾
    -0.09
    ÅŁÄ±k
    -0.09
    POSITIVE LOGITS
    åłĩ
    0.11
    çĩĥ
    0.09
    è¹ģ
    0.09
    èĪŀ
    0.09
     Ballet
    0.09
    ç¿©
    0.09
    åĬ¨ä½ľ
    0.09
     Pir
    0.08
     Curtain
    0.08
    DDL
    0.08
    Activations Density 0.072%

    No Known Activations