© 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. 61728
    Prev
    Next
    INDEX
    Explanations

    companies acquiring

    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
    ä¾Ŀèµĸ
    -0.09
    æĬ½åĩº
    -0.08
    æݺ
    -0.08
    èĩªåѦ
    -0.08
     circ
    -0.08
    dependency
    -0.08
    å¯ĵæĦı
    -0.08
    åĴĮ个人
    -0.08
    inqu
    -0.08
    夹
    -0.08
    POSITIVE LOGITS
    æĶ¶è´Ń
    0.15
     acquisition
    0.13
     acquisitions
    0.12
    并è´Ń
    0.11
    åIJĪ并
    0.11
     Acquisition
    0.11
    æķ´åIJĪ
    0.11
     acquire
    0.11
     acquired
    0.10
     merger
    0.10
    Activations Density 0.126%

    No Known Activations