© 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. 53668
    Prev
    Next
    INDEX
    Explanations

    gas emissions or CO2 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
    ¢åįķ
    -0.10
    ä¸Ģå¥Ĺ
    -0.10
    orate
    -0.09
    æģ°å½ĵ
    -0.09
    åħ¸èĮĥ
    -0.09
    OrCreate
    -0.09
    éħ¬
    -0.09
    æĪIJé¾Ļ
    -0.09
    éºĴ
    -0.09
    edata
    -0.09
    POSITIVE LOGITS
    4
    0.11
    3
    0.11
    5
    0.10
    2
    0.10
    6
    0.10
    8
    0.10
    1
    0.10
    9
    0.10
    7
    0.10
    bul
    0.09
    Activations Density 0.019%

    No Known Activations