© 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. 56851
    Prev
    Next
    INDEX
    Explanations

    geographic, statistical, architectural, sonic

    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
    èİ·å¾ĹæĽ´å¤ļ
    -0.11
    mPid
    -0.10
    uten
    -0.09
    åĮĸè¿Ľç¨ĭ
    -0.09
     ones
    -0.09
    é¦Ļåij³
    -0.09
    æĢģ
    -0.09
    APS
    -0.09
    ityEngine
    -0.09
    åĪ©çĶ¨çİĩ
    -0.09
    POSITIVE LOGITS
    urally
    0.09
    æ´¼
    0.08
    æ¡¥æ¢ģ
    0.08
    误åĮº
    0.08
    ertz
    0.08
    èĿĮ
    0.08
    aines
    0.08
    天èµĭ
    0.08
    ally
    0.08
    çijŀ士
    0.08
    Activations Density 0.193%

    No Known Activations