© 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. 17156
    Prev
    Next
    INDEX
    Explanations

    other or no other

    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
    èĭ¥å¹²
    -0.11
    ä¹Łæľīä¸ĢäºĽ
    -0.09
    ä¸ĢäºĽ
    -0.09
    phalt
    -0.09
    ä¸įåĨįæĺ¯
    -0.08
    ä¸Ģè§Ĵ
    -0.08
    ä¹Łæľīå¾Īå¤ļ
    -0.08
    çļĦä¸ĢäºĽ
    -0.08
    raries
    -0.08
    两大
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ人
    0.10
     سÙĪÙī
    0.10
     nor
    0.10
    æľīä»»ä½ķ
    0.09
    å®ŀè´¨æĢ§
    0.09
    ilor
    0.09
    ä»»ä½ķä¸Ģ个
    0.09
    çĿĢåĬĽ
    0.09
    nor
    0.08
    æĥº
    0.08
    Activations Density 0.023%

    No Known Activations