© 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. 33496
    Prev
    Next
    INDEX
    Explanations

    possessive determiners followed by personal/business outcomes

    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
    æ·¼
    -0.09
    esson
    -0.09
    OTION
    -0.08
    ç©·
    -0.08
     virt
    -0.08
    lc
    -0.08
    æĺ¶
    -0.08
    oi
    -0.08
    ç´§å¯Ĩ
    -0.08
    ÙģاÙĦ
    -0.08
    POSITIVE LOGITS
     chances
    0.13
     overall
    0.11
    æĬµæĬĹ
    0.10
    0.10
     ability
    0.10
    è¾Ī
    0.10
    驾é©Ń
    0.10
    æĪIJ为ä¸Ģ个
    0.09
    åºĶ对
    0.09
    人们çļĦ
    0.09
    Activations Density 0.075%

    No Known Activations