© 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. 29834
    Prev
    Next
    INDEX
    Explanations

    drive, drives, driven

    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
    éĢł
    -0.10
    åħijçİ°
    -0.10
    å¡ŀ
    -0.09
    æĴĤ
    -0.09
    æķħæĦı
    -0.09
     Tig
    -0.08
    è¡·å¿ĥ
    -0.08
    å°¾
    -0.08
    ä»°
    -0.08
    ä½ĵåĬĽ
    -0.08
    POSITIVE LOGITS
    驱
    0.12
    éªĸ
    0.11
     drive
    0.11
    驱åĬ¨
    0.11
    .drive
    0.10
     Drive
    0.10
     drives
    0.10
    ä¸ĢçĤ¹ä¹Łä¸į
    0.10
    æŀī
    0.09
    haft
    0.09
    Activations Density 0.052%

    No Known Activations