© 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. 58694
    Prev
    Next
    INDEX
    Explanations

    automated / automatically

    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
    å±ŀ
    -0.11
    æĻĸ
    -0.10
    使ä¹ĭ
    -0.09
    shade
    -0.09
    å¤Ń
    -0.09
     Byrne
    -0.09
    å±ŀäºİ
    -0.09
    ãĤ¤ãĥ¤
    -0.09
    adoo
    -0.09
    对她
    -0.08
    POSITIVE LOGITS
    /auto
    0.13
    åĮĸçļĦ
    0.13
    èĩªåĬ¨
    0.12
     automatically
    0.10
    èĩªåĬ¨åĮĸ
    0.10
    æĹłäºº
    0.10
    (auto
    0.09
    åħ¨èĩªåĬ¨
    0.09
     auto
    0.09
    automatic
    0.09
    Activations Density 0.068%

    No Known Activations