© 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. 4275
    Prev
    Next
    INDEX
    Explanations

    past tense verbs after have/has

    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
    å¾Īå¤ļäºĭæĥħ
    -0.12
     GANG
    -0.10
    ubs
    -0.10
    èĿĻ
    -0.09
    PHPUnit
    -0.09
     Hamp
    -0.09
    åħ®
    -0.09
    beth
    -0.08
    HITE
    -0.08
    æĹ¥æ¶Īæģ¯
    -0.08
    POSITIVE LOGITS
    çīĴ
    0.09
    /how
    0.09
    éļ³
    0.09
    æ¥ł
    0.08
    éĶĻäºĨ
    0.08
    æĸ°åĬ¨èĥ½
    0.08
    æĶ¾è¿Ľ
    0.08
    çŃ¹çłģ
    0.08
    iner
    0.08
    æī¿æĭħ责任
    0.08
    Activations Density 0.057%

    No Known Activations