© 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. 52747
    Prev
    Next
    INDEX
    Explanations

    representative

    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
    strap
    -0.12
    teenth
    -0.11
    å±ij
    -0.10
    æݾ
    -0.09
    åĴ¨è¯¢æľįåĬ¡
    -0.09
    ัà¸Ļ
    -0.09
    pendicular
    -0.09
    ä¿ĿæĬ¤åĮº
    -0.09
    çıŃ车
    -0.09
    ian
    -0.08
    POSITIVE LOGITS
    们
    0.10
    ÏĤ
    0.10
     Sized
    0.10
    -sized
    0.10
    åı¸
    0.09
    们çļĦ
    0.09
    coni
    0.09
    ouri
    0.09
    ÑıÑħ
    0.09
    orado
    0.08
    Activations Density 0.015%

    No Known Activations