© 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. 62197
    Prev
    Next
    INDEX
    Explanations

    balance due, taxes, money, high insurance, debt, sums, role

    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
    vit
    -0.10
    ä¸ĸä¿Ĺ
    -0.10
    éĤĢ请
    -0.09
    èĥĮ
    -0.09
    çģµåĬ¨
    -0.09
    åIJ¦
    -0.09
    å®ıè§Ĥ
    -0.09
    pei
    -0.09
     dispens
    -0.09
    ibling
    -0.08
    POSITIVE LOGITS
    æ»ŀ
    0.11
    çļĦæĢģ度
    0.10
    æľ¬è½®
    0.09
    éĢı
    0.09
    éĢĥ
    0.09
    .methods
    0.09
     Att
    0.09
    ä¸ĵ项è¡ĮåĬ¨
    0.09
    çIJĨ
    0.08
    (TIM
    0.08
    Activations Density 0.050%

    No Known Activations