© 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. 30989
    Prev
    Next
    INDEX
    Explanations

    strict code blocks

    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
    à´Ł
    -0.10
    æŀķ
    -0.10
    仲
    -0.09
    æĺ¶
    -0.09
    æŀķ头
    -0.09
    é¹£
    -0.09
    ä¸ĢæĿ¯
    -0.08
    éħ¹
    -0.08
    éĻĮçĶŁ
    -0.08
    å¼ĢæĿ¥
    -0.08
    POSITIVE LOGITS
    è¯
    0.09
    æIJ¦
    0.09
    ifu
    0.09
     обо
    0.09
    oug
    0.08
    umbing
    0.08
    éĵİ
    0.08
    容纳
    0.08
    åİĭåĪ¶
    0.08
    çŃijçī¢
    0.08
    Activations Density 0.008%

    No Known Activations