© 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. 18857
    Prev
    Next
    INDEX
    Explanations

    iodine and iodinated compounds

    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
    å¤ĸæı´
    -0.10
    æģĴ
    -0.10
    .Help
    -0.10
    reet
    -0.10
     Affero
    -0.09
    hton
    -0.09
    iaux
    -0.09
    çıŃåŃIJ
    -0.08
    é¦
    -0.08
    ural
    -0.08
    POSITIVE LOGITS
    æĹ¥å¸¸çĶŁæ´»
    0.09
    иÑĢован
    0.08
    atto
    0.08
     Parade
    0.08
    æ§İ
    0.08
    æ´¾
    0.08
    äºĨä¸Ģ个
    0.08
    ä¸Ģèµ·åİ»
    0.08
    IPC
    0.08
     Maritime
    0.08
    Activations Density 0.066%

    No Known Activations