© 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. 23033
    Prev
    Next
    INDEX
    Explanations

    radiotherapy cancer treatment

    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
    conte
    -0.09
    æ²»å®ī
    -0.09
     ram
    -0.09
    æŀ¹
    -0.09
    èĤ¡æľ¬
    -0.09
    æĸĩç«łæĿ¥æºIJ
    -0.09
    æĦıè¯Ĩ
    -0.08
    repid
    -0.08
    éĻ¨
    -0.08
     mies
    -0.08
    POSITIVE LOGITS
    è¾IJå°Ħ
    0.09
    è½²
    0.09
    çħ§å°Ħ
    0.09
    æĶ¾å°Ħ
    0.09
     soph
    0.09
    æĢľ
    0.09
    çijĽ
    0.09
    æĸ½
    0.09
    _TARGET
    0.09
    å°Ħ
    0.08
    Activations Density 0.301%

    No Known Activations