© 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. 49205
    Prev
    Next
    INDEX
    Explanations

    clinical trial stages and drug approval

    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
    åĤį
    -0.09
    å¨ĺ
    -0.09
    ounty
    -0.09
    æĬ«
    -0.08
    æµ´
    -0.08
     mum
    -0.08
    çľĭäºĨä¸Ģ
    -0.08
    缴è¾ĸ
    -0.08
    OTA
    -0.08
    åĪ®
    -0.08
    POSITIVE LOGITS
    å¸ĤåľºéľĢæ±Ĥ
    0.11
    å¸ĤåľºçļĦ
    0.11
     markets
    0.10
    å¸Ĥåľºè§Ħ模
    0.10
    ä¸Ĭå¸Ĥ
    0.10
    欧ç¾İ
    0.10
    æľīæķĪæĢ§
    0.10
    åĮĹç¾İ
    0.10
     marketer
    0.09
     ÑĢÑĭн
    0.09
    Activations Density 0.330%

    No Known Activations