© 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. 39020
    Prev
    Next
    INDEX
    Explanations

    dental and cosmetic restoration

    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
    èĶĮ
    -0.09
    еннÑĭй
    -0.08
    IRR
    -0.08
    ãĦ§
    -0.08
    æĭīæĸ¯
    -0.08
    带çĿĢ
    -0.08
    帶èijĹ
    -0.08
    æŃ£æĺ¯åĽłä¸º
    -0.08
    订
    -0.08
    æĬķ稿
    -0.08
    POSITIVE LOGITS
    媳
    0.09
    åľ¨å¤ĸ
    0.09
    .ini
    0.09
     cracks
    0.08
    éĽķ
    0.08
    åħī纤
    0.08
    çļĦé¢ľèī²
    0.08
     scratch
    0.08
    urn
    0.08
    Col
    0.08
    Activations Density 0.086%

    No Known Activations