© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 858
    Prev
    Next
    INDEX
    Explanations

    chromium and chrome

    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
    Negative Logits
     Simpsons
    -0.09
    /preferences
    -0.09
    tra
    -0.08
    æ¤į
    -0.08
    æ²Ļåıij
    -0.08
    une
    -0.08
    oka
    -0.08
    èĨ³
    -0.08
    ä¸Ńç§ij
    -0.08
    preferences
    -0.07
    POSITIVE LOGITS
    æ¿ij
    0.11
    phem
    0.11
    æĩ¿
    0.10
    éĢį
    0.09
    æģIJæħĮ
    0.09
     اÙĦبع
    0.08
    obile
    0.08
    æįĭ
    0.08
    ToObject
    0.08
    çłº
    0.08
    Activations Density 0.012%

    No Known Activations