© 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. 23507
    Prev
    Next
    INDEX
    Explanations

    accusations against

    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
    åįĹåĮĹ
    -0.11
    èĻļåģĩ
    -0.09
    ستر
    -0.09
    对å¤ĸ
    -0.09
    é«ĺæīĭ
    -0.09
    å¤ĸçķĮ
    -0.09
    èĢĮæĪIJ
    -0.09
    yz
    -0.08
    对åħ¶
    -0.08
    çĿ¦
    -0.08
    POSITIVE LOGITS
    è¿Ļ座åŁİå¸Ĥ
    0.09
     Tiên
    0.09
    桧
    0.09
    åħ·æľīèī¯å¥½
    0.09
    .dex
    0.08
    è¿Ī
    0.08
    åıĮèĦļ
    0.08
    JOR
    0.08
    éĢĤ
    0.08
    æ²¹èĦĤ
    0.08
    Activations Density 0.034%

    No Known Activations