© 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. 53136
    Prev
    Next
    INDEX
    Explanations

    computer vision and image processing

    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
     Mozilla
    -0.09
    .alt
    -0.08
    æĸĮ
    -0.08
    ูà¸ģ
    -0.08
    otron
    -0.07
     statements
    -0.07
    ath
    -0.07
     lắng
    -0.07
    EMS
    -0.07
    èĥ³
    -0.07
    POSITIVE LOGITS
    积水
    0.11
    åĬłæ²¹ç«Ļ
    0.10
    åĽ¾åĥı
    0.10
    opencv
    0.10
    è§Ĩè§ī
    0.10
    å¾ĹæĦı
    0.09
     image
    0.09
    avin
    0.09
    æıIJåıĸ
    0.09
    (image
    0.08
    Activations Density 0.384%

    No Known Activations