© 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. 27370
    Prev
    Next
    INDEX
    Explanations

    islands

    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
    大海
    -0.10
    滨海
    -0.09
    æĢ¦
    -0.09
    ç¼ļ
    -0.09
    ect
    -0.09
    ometrics
    -0.08
    .datasource
    -0.08
     bench
    -0.08
    太平æ´ĭ
    -0.08
    å°º
    -0.08
    POSITIVE LOGITS
    两岸
    0.13
    èīĦ
    0.12
     docking
    0.10
    è¦ģæĥ³
    0.10
    èIJ¥åľ°
    0.10
    岸边
    0.10
    é¹Ī
    0.09
    æĭĸ
    0.09
    èĪ¸
    0.09
    çłģ头
    0.09
    Activations Density 0.087%

    No Known Activations