© 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. 57906
    Prev
    Next
    INDEX
    Explanations

    burning biomass and fossil fuels

    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
    toolbox
    -0.09
    ῦ
    -0.08
    æį·
    -0.08
    à¤ŀ
    -0.08
    æİ¥åı£
    -0.08
    omid
    -0.08
    oved
    -0.08
    éĿĵ丽
    -0.08
    æ°´éĿ¢
    -0.08
    å¼ĢéŨ
    -0.08
    POSITIVE LOGITS
    çĦļçĥ§
    0.13
    çĦļ
    0.13
    çĤī
    0.11
    BT
    0.10
    ide
    0.09
    ç¯Ŀ
    0.09
    éĶħçĤī
    0.09
     BT
    0.09
     Comb
    0.09
    æī§
    0.09
    Activations Density 0.070%

    No Known Activations