© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10156
    Prev
    Next
    INDEX
    Explanations

    words ending in -ing, -ating, -oding

    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
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.09
    ingly
    -0.09
    Ãłnh
    -0.09
    ëį°
    -0.09
    ç«ŀæĬĢ
    -0.09
    pery
    -0.09
    ä¸ĢéĿ¢
    -0.09
    æµ·åı£
    -0.08
    _arch
    -0.08
    è¿Ļæĺ¯åĽłä¸º
    -0.08
    POSITIVE LOGITS
     ourselves
    0.10
     oneself
    0.09
    echo
    0.08
     каÑĩеÑģÑĤв
    0.08
    æľĽ
    0.08
    çļĦè¿ĩç¨ĭä¸Ń
    0.08
    ç³Ł
    0.08
    çĺ¦
    0.08
    ä¹ħäºĨ
    0.08
    /testing
    0.08
    Activations Density 0.313%

    No Known Activations