© 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. 22498
    Prev
    Next
    INDEX
    Explanations

    . Theory, Phy, H, The, New, Op, 1, Iso

    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
    为ä¹ĭ
    -0.11
    ãģĹãģĭãĤĤ
    -0.10
    è¿ĽèĢĮ
    -0.10
    éļ¹
    -0.10
    æĪĸå°Ĩ
    -0.09
    åį´åıĪ
    -0.09
    ä½Ĩä»ĸ们
    -0.09
    讫
    -0.09
    èĢĮ对äºİ
    -0.09
     THEIR
    -0.09
    POSITIVE LOGITS
    æľīçĶ¨
    0.09
    .boost
    0.08
    天çĶŁ
    0.07
     reint
    0.07
    REV
    0.07
    顺åºĶ
    0.07
    èijĹä½ľ
    0.07
    æĹłæĦı
    0.07
    ãĢĮ
    0.07
     Ton
    0.07
    Activations Density 0.215%

    No Known Activations