© 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. 18707
    Prev
    Next
    INDEX
    Explanations

    form or forms

    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
    è¿Ļä¹Ī大
    -0.08
    çĶ¨éĢĶ
    -0.08
     glue
    -0.08
    è¿Ļç§įæĥħåĨµ
    -0.08
    urv
    -0.08
     ke
    -0.08
    尺度
    -0.08
    kee
    -0.08
    arrow
    -0.08
    Proposal
    -0.07
    POSITIVE LOGITS
    ä¸įå®Į
    0.10
    éĺħ读åħ¨æĸĩ
    0.10
    èµı
    0.10
    lements
    0.10
    主åħ¬
    0.10
    åĴĮæĶ¯æĮģ
    0.10
    enci
    0.09
    妾
    0.09
    äºĨè§£æĽ´å¤ļ
    0.09
    erdem
    0.09
    Activations Density 0.013%

    No Known Activations