© 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. 23263
    Prev
    Next
    INDEX
    Explanations

    quoted speech context

    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
    æ¯Ķå¦Ĥ说
    -0.10
    æĺ¯ä»Ģä¹Īåij¢
    -0.10
    LETE
    -0.10
    åĺĽ
    -0.09
    appen
    -0.09
    并ä¸Ķ
    -0.09
    åĵī
    -0.09
     Carlson
    -0.08
    å°ıç¼ĸä¸Ģèµ·
    -0.08
     маÑģÑĤ
    -0.08
    POSITIVE LOGITS
    æķ´ä¸ª
    0.10
    åĩłä¹İæīĢæľī
    0.09
    没æľī人
    0.09
    æīĢæľī
    0.09
    æīĢæľī人éĥ½
    0.09
    ä¸ĢåĪĩ
    0.09
     nobody
    0.09
    人人
    0.09
    ä¸ĢåĪĩéĥ½æĺ¯
    0.09
    åıªè¦ģæĺ¯
    0.08
    Activations Density 0.028%

    No Known Activations