© 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. 33874
    Prev
    Next
    INDEX
    Explanations

    `add`, `let`, `cut`, `read`

    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
    æľĢç»Ī
    -0.12
    æľĢåIJİ
    -0.10
    ç»Īäºİ
    -0.09
    åıįæŃ£
    -0.09
    æľĢçµĤ
    -0.09
    çµĤæĸ¼
    -0.09
    æĺ¯ä¸Ģ
    -0.09
    éļ¾åħį
    -0.09
     finally
    -0.09
    æ²Ķ
    -0.09
    POSITIVE LOGITS
    æ´¾
    0.09
    ẻ
    0.09
    串
    0.09
    æŀľ
    0.08
     niên
    0.08
    eting
    0.08
    æĭĽ
    0.08
    çļĦä¸ĢéĿ¢
    0.08
    çĿĢæīĭ
    0.08
    æĪIJçĨŁçļĦ
    0.08
    Activations Density 0.224%

    No Known Activations