© 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. 33133
    Prev
    Next
    INDEX
    Explanations

    apostrophe contractions ('t, 's, 'd, 'm, 'h)

    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
    iales
    -0.11
    çļĦå°±æĺ¯
    -0.10
    ç´§
    -0.09
    说å®ŀè¯Ŀ
    -0.09
    ially
    -0.09
    quet
    -0.08
     Monkey
    -0.08
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    atial
    -0.08
    elor
    -0.08
    POSITIVE LOGITS
    é¼ĵ
    0.09
    å¹²æ¶ī
    0.09
    çŨ
    0.09
    .qq
    0.09
    odox
    0.09
    ÑĮÑİ
    0.09
    åĿ¨
    0.08
     ÑĩиÑģл
    0.08
    æľĢç¾İçļĦ
    0.08
     tiá»ĥu
    0.08
    Activations Density 0.085%

    No Known Activations