© 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. 11023
    Prev
    Next
    INDEX
    Explanations

    sewing and sew machines

    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
     Pipes
    -0.11
    缴
    -0.10
    æĵİ
    -0.10
    磴
    -0.09
     Patt
    -0.09
    /ros
    -0.08
    NAL
    -0.08
     окÑĢÑĥг
    -0.08
    èĩªæĦ¿
    -0.08
    åħ´èµ·
    -0.08
    POSITIVE LOGITS
    ç¼Ŀ
    0.11
     Coh
    0.10
    åĶ§
    0.10
    裨
    0.10
    é¢į
    0.10
    åŁĭ
    0.10
    åĴĮå®ĮåĸĦ
    0.10
    æĶ¶å½ķ
    0.10
    åıįèĢĮ
    0.09
    äºĨ大éĩıçļĦ
    0.09
    Activations Density 0.073%

    No Known Activations