© 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. 62152
    Prev
    Next
    INDEX
    Explanations

    proper nouns after 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
    大çĨĬçĮ«
    -0.10
    é¢
    -0.09
    Ùħات
    -0.09
    çľ¨çľ¼
    -0.09
    chia
    -0.08
    çľĭ书
    -0.08
    ç¥İ
    -0.08
     astronomical
    -0.08
    åı¯æĥ³
    -0.08
     uÄŁ
    -0.08
    POSITIVE LOGITS
    两ç§į
    0.12
     two
    0.12
    两类
    0.11
     several
    0.10
    ä¸īç§į
    0.10
     seguint
    0.10
    两款
    0.09
    两个
    0.09
    两大
    0.09
    ä¸Ģç§į
    0.09
    Activations Density 0.641%

    No Known Activations