© 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. 50059
    Prev
    Next
    INDEX
    Explanations

    well followed by prepositions

    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
    achs
    -0.10
    ering
    -0.09
    жи
    -0.09
    æĤ»
    -0.09
    ÑĢажа
    -0.09
    å·®çĤ¹
    -0.09
    线索
    -0.09
    æľīèĥ½åĬĽ
    -0.09
    红线
    -0.09
    æĴ¬
    -0.09
    POSITIVE LOGITS
    åĵī
    0.09
    æĶ¶æĭ¾
    0.08
     bru
    0.08
    æĸ¯é¡¿
    0.08
    åıĭ们
    0.08
    ä½ıäºĨ
    0.08
    klass
    0.08
    çݰ代åĮĸ
    0.08
    ä¾£
    0.08
     ÑģÑĢедне
    0.08
    Activations Density 0.030%

    No Known Activations