© 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. 39884
    Prev
    Next
    INDEX
    Explanations

    carbon capture, acidification, valorization

    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
    æ±ŀ
    -0.10
    æ²Ł
    -0.10
     Junction
    -0.09
    å½¼æѤ
    -0.09
    ç³Ļ
    -0.09
    itional
    -0.08
     conting
    -0.08
    mental
    -0.08
    缸äºĴ
    -0.08
    umu
    -0.08
    POSITIVE LOGITS
    大çģ«
    0.10
    大æĪ·
    0.10
     ë¬
    0.09
    èĢģèĻİ
    0.09
    被æįķ
    0.09
    伶
    0.09
     soundtrack
    0.09
    åĩıæİĴ
    0.09
    æ°Ķ
    0.09
    asan
    0.09
    Activations Density 0.048%

    No Known Activations