© 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. 49051
    Prev
    Next
    INDEX
    Explanations

    oxygen treatment or generators

    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
    åģľçĶµ
    -0.10
    éŨå¤ĸ
    -0.09
    溯æºIJ
    -0.09
    åĶ±çīĩ
    -0.09
    æ±īåŃIJ
    -0.08
    çļĦéĴ±
    -0.08
    身åŃIJ
    -0.08
    èĿ®
    -0.08
    æľīçĤ¹
    -0.08
    å¤ļäºĨ
    -0.08
    POSITIVE LOGITS
    æ°§æ°Ķ
    0.11
     Oxygen
    0.11
     oxygen
    0.10
    æĸĩæ¡£
    0.09
    æ°§
    0.09
    æ®Ĭ
    0.09
    xygen
    0.09
     rfl
    0.09
    elier
    0.08
    çĸĹ
    0.08
    Activations Density 0.053%

    No Known Activations