© 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. 55154
    Prev
    Next
    INDEX
    Explanations

    pharmaceuticals and manufacturing guidelines

    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
    Ñįм
    -0.10
    нÑıÑĤ
    -0.09
    ulist
    -0.09
     ка
    -0.09
    æĪIJé¾Ļ
    -0.09
    åľ°æ¯¯
    -0.09
     ÑįнеÑĢги
    -0.09
    .jet
    -0.09
    æĬĢå¸Ī
    -0.09
    éĽī
    -0.08
    POSITIVE LOGITS
    èį¯åĵģ
    0.15
    åĪ¶èį¯
    0.13
    æŀ¸
    0.12
    èį¯ä¸ļ
    0.11
     pharmaceutical
    0.11
    åIJĪè§Ħ
    0.11
    èį¯çī©
    0.11
     Pharma
    0.10
    FDA
    0.10
     FDA
    0.10
    Activations Density 0.213%

    No Known Activations