© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51644
    Prev
    Next
    INDEX
    Explanations

    n-3 fatty acids

    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
    讫
    -0.09
    éļİ段
    -0.09
    olem
    -0.09
    DeviceInfo
    -0.09
    æĽ¿
    -0.09
    iram
    -0.08
    éŃĶæľ¯
    -0.08
    åħ¨å¤©
    -0.08
    æĭŁ
    -0.08
    din
    -0.08
    POSITIVE LOGITS
    æݨ
    0.10
    æij©
    0.10
    é²Ń
    0.09
    ãĥĬãĥ«
    0.09
    é²±
    0.09
    ndef
    0.09
    ä¸įå¾Ĺè¶ħè¿ĩ
    0.09
     Gef
    0.09
    ç»Ĩèħ»
    0.09
    俱
    0.08
    Activations Density 0.222%

    No Known Activations