© 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. 35295
    Prev
    Next
    INDEX
    Explanations

    to no avail

    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
    ÑıÑī
    -0.10
    仪表
    -0.09
     coh
    -0.09
    横åIJij
    -0.08
    ªĮ
    -0.08
    æĥ³èµ·äºĨ
    -0.08
    èį
    -0.08
    imas
    -0.08
    åĿª
    -0.08
    çīĪæĿĥ声æĺİ
    -0.08
    POSITIVE LOGITS
    fully
    0.09
     ÙħÙĨÙĩا
    0.08
     turb
    0.08
    ä¸Ģ次
    0.08
    ances
    0.08
    DDD
    0.08
    oso
    0.08
    主ä¹ī
    0.08
    able
    0.08
     recl
    0.08
    Activations Density 0.002%

    No Known Activations