© 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. 30622
    Prev
    Next
    INDEX
    Explanations

    verbs of change or continuation

    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
    å¾Īå¿«
    -0.11
    lim
    -0.09
    çī¹çĤ¹æĺ¯
    -0.09
    å§Ķä¼ļ
    -0.09
    wick
    -0.09
    åİĿ
    -0.09
    лим
    -0.09
    å¾Īæľī
    -0.09
    antu
    -0.09
    é¡·
    -0.09
    POSITIVE LOGITS
    maal
    0.10
    å¾ĹæĦı
    0.09
     Eig
    0.09
    fos
    0.09
    /if
    0.09
    棹
    0.08
    âĸ¸
    0.08
    ãģ£ãģŁãĤī
    0.08
     _______,
    0.08
    oe
    0.08
    Activations Density 0.105%

    No Known Activations