© 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. 22906
    Prev
    Next
    INDEX
    Explanations

    coconut

    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
    æĺ¯ä¸Ģ件
    -0.10
    æ²Ľ
    -0.09
    è¾ŀ
    -0.09
    å¹ħ
    -0.09
    ä¿¡æģ¯åħ¬å¼Ģ
    -0.09
    ä¹ĸ
    -0.09
    åłĩ
    -0.09
    çĥ«
    -0.08
    ä¹ĸä¹ĸ
    -0.08
    碳éħ¸
    -0.08
    POSITIVE LOGITS
    椰
    0.12
    éĥ¨éķ¿
    0.10
    屿
    0.10
    éĢłèĪ¹
    0.10
    æ¸Ķæ°ij
    0.09
     coconut
    0.09
    æ¼Ķ示
    0.09
    åīĬ
    0.09
     Coconut
    0.09
    PEAR
    0.09
    Activations Density 0.057%

    No Known Activations