© 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. 6573
    Prev
    Next
    INDEX
    Explanations

    numbers followed by specific words

    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
    çļĦç»ıåħ¸
    -0.10
    ä¸Ģéĥ¨åĪĨ
    -0.10
     Toys
    -0.09
    ãĤĵãģ©
    -0.09
    éļĭ
    -0.09
    ehr
    -0.09
    两ç§į
    -0.09
    æŶæŶ
    -0.08
    ÑĪе
    -0.08
    ä¸Ģç«Ļ
    -0.08
    POSITIVE LOGITS
    çłŃ
    0.09
    intern
    0.09
    zes
    0.08
    GU
    0.08
    fcn
    0.08
    åŁŁ
    0.08
    æłİ
    0.08
    æĮij
    0.08
    å®ŀäºĭ
    0.08
    鼷æĸ¯
    0.08
    Activations Density 0.098%

    No Known Activations