© 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. 36756
    Prev
    Next
    INDEX
    Explanations

    takes over or place

    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
    æĸ°çļĦä¸Ģ
    -0.09
     sơ
    -0.09
    èĢħçļĦ
    -0.09
     cáºŃp
    -0.09
    åłª
    -0.09
    åĩºè·¯
    -0.09
    æĨ¬
    -0.08
    ogan
    -0.08
    ambi
    -0.08
    主åĬ¨æĢ§
    -0.08
    POSITIVE LOGITS
    uration
    0.10
    èĻIJå¾ħ
    0.09
    ä¸ĩåįĥ
    0.08
    pies
    0.08
    åĩ¸
    0.08
    ipelines
    0.08
    éĹ«
    0.08
    人们
    0.08
    è½®åĽŀ
    0.08
    æī¹åĪ¤
    0.08
    Activations Density 0.050%

    No Known Activations