© 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. 10405
    Prev
    Next
    INDEX
    Explanations

    methane gas production

    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
    诱
    -0.11
    人æµģ
    -0.10
    çģ°å°ĺ
    -0.10
    æ¥ŀ
    -0.09
    ä¼łçľŁ
    -0.09
    æĬŁ
    -0.09
    éľĸ
    -0.09
    èĽĽ
    -0.09
    宦
    -0.09
    ÅĽÄĩ
    -0.09
    POSITIVE LOGITS
    æ°Ķä½ĵ
    0.13
     gas
    0.12
     fart
    0.12
    å±ģ
    0.11
    åı£æ°Ķ
    0.10
    éħįä¸Ĭ
    0.10
    æ°Ķ
    0.10
    天çĦ¶æ°Ķ
    0.10
    åĹĿ
    0.10
     bur
    0.09
    Activations Density 0.092%

    No Known Activations