© 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. 56110
    Prev
    Next
    INDEX
    Explanations

    with followed by 'the' or 'a'

    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
    inker
    -0.11
    çľ¼åīįçļĦ
    -0.09
    æī¶
    -0.09
    å°»
    -0.09
    é»Ħæĺı
    -0.09
    è¾ĵ
    -0.09
     اÙĦØ£ÙĨ
    -0.08
    æĭĽåij¼
    -0.08
    è¯įæĿ¡
    -0.08
     è¾ĵ
    -0.08
    POSITIVE LOGITS
    isy
    0.09
    æĹ¥æĬ¥ç¤¾
    0.09
    ä¸įåĩº
    0.09
     yüz
    0.08
    赤
    0.08
    çīĽ
    0.08
    éģ¿å¼Ģ
    0.08
    è¿Ļç§įæĸ¹æ³ķ
    0.08
    çªģ
    0.07
    æѤ
    0.07
    Activations Density 0.130%

    No Known Activations