© 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. 30139
    Prev
    Next
    INDEX
    Explanations

    training events and sessions

    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
    ä¹ĭæĥħ
    -0.10
    éĹ®åĢĻ
    -0.09
    æ³Ħ
    -0.09
    æĺ¥æĻļ
    -0.09
    uppy
    -0.09
    èĭ«
    -0.09
    èĢĥåľº
    -0.09
    æĥ³èµ·æĿ¥
    -0.08
    ä»Ĩ
    -0.08
    代è¨Ģ人
    -0.08
    POSITIVE LOGITS
    讲座
    0.17
     workshops
    0.15
     workshop
    0.11
    çłĶ讨ä¼ļ
    0.10
     sessions
    0.10
     занÑıÑĤ
    0.10
     session
    0.10
    ä¸Ģç³»åĪĹ
    0.09
     Workshop
    0.09
    è¿ĺä¸įå¤Ł
    0.09
    Activations Density 0.087%

    No Known Activations