© 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. 33189
    Prev
    Next
    INDEX
    Explanations

    veterinary medicine and practice

    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
     mon
    -0.08
    èĢģ人
    -0.08
    cco
    -0.08
    cep
    -0.08
    ose
    -0.08
    RN
    -0.07
    getData
    -0.07
     Creat
    -0.07
     picker
    -0.07
    åª
    -0.07
    POSITIVE LOGITS
    åħ½
    0.15
    çį¸
    0.13
    æī§ä¸ļ
    0.11
     Vet
    0.11
    饲
    0.11
    çķľ
    0.10
     veterinary
    0.10
    仵
    0.10
    é»ĺ
    0.10
    å¾·æĭī
    0.10
    Activations Density 0.104%

    No Known Activations