© 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. 54315
    Prev
    Next
    INDEX
    Explanations

    climate change emissions

    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
    åĹij
    -0.10
    å¼ĢæĿ¥
    -0.10
    æģĻ
    -0.10
     Kou
    -0.09
    ä¸Ģè¶Ł
    -0.09
     Hull
    -0.09
    HSV
    -0.09
    èµ°åĩºæĿ¥
    -0.09
    æª
    -0.08
    çĸ²åĬ³
    -0.08
    POSITIVE LOGITS
    碳
    0.18
     carbon
    0.17
    äºĮæ°§åĮĸ碳
    0.17
    æ°ĶåĢĻåıĺåĮĸ
    0.16
    温室
    0.15
    çĤŃ
    0.15
     CO
    0.15
     Carbon
    0.14
    carbon
    0.14
    ä½İ碳
    0.14
    Activations Density 0.072%

    No Known Activations