© 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. 34278
    Prev
    Next
    INDEX
    Explanations

    formulated, recipe, blender, components, wireless

    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
    Pixels
    -0.10
    æĬ½
    -0.10
    .openg
    -0.09
     ÑĤÑĢÑĥб
    -0.09
    Verts
    -0.09
    åIJĥçļĦ
    -0.09
    èĿĪ
    -0.09
    омеÑĢ
    -0.09
     Chew
    -0.09
    вал
    -0.09
    POSITIVE LOGITS
    éħįæĸ¹
    0.18
    éħįæĸĻ
    0.12
    è°ĥéħį
    0.11
    0
    0.11
     mixture
    0.10
    æ··åIJĪ
    0.10
     recipe
    0.10
     recipes
    0.10
    æĪIJåĪĨ
    0.10
    çłĶåıij
    0.10
    Activations Density 0.154%

    No Known Activations