© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9757
    Prev
    Next
    INDEX
    Explanations

    climate change and global warming

    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
    ton
    -0.10
    æīĵæī®
    -0.09
    çĸĥ
    -0.09
    éĿĻæĢģ
    -0.09
    修补
    -0.09
    _decision
    -0.09
    TON
    -0.09
    åį§
    -0.09
    ç»ıè´¸
    -0.09
    ãĥĬãĥ³
    -0.09
    POSITIVE LOGITS
    æ°ĶåĢĻåıĺåĮĸ
    0.14
     climate
    0.13
    æ°ĶåĢĻ
    0.11
     change
    0.11
    climate
    0.11
     Climate
    0.10
    Climate
    0.10
     Change
    0.09
    æ°Ķ温
    0.09
    change
    0.09
    Activations Density 0.082%

    No Known Activations