© 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. 38809
    Prev
    Next
    INDEX
    Explanations

    fill the gap

    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
     Rig
    -0.10
    æĸ¹å¼ıè¿Ľè¡Į
    -0.10
    è¾ŀ
    -0.09
     kurulu
    -0.08
    .fixed
    -0.08
    æģ
    -0.08
    à¸ĩ
    -0.08
    åı¦ä¸ĢåįĬ
    -0.08
    æĦıæĢĿ
    -0.08
    çIJĨæĥ³çļĦ
    -0.08
    POSITIVE LOGITS
    å¡«è¡¥
    0.30
    弥补
    0.22
     fill
    0.17
    è¡¥é½IJ
    0.16
    缺åı£
    0.16
    fill
    0.16
    ç½ħ
    0.15
     fills
    0.15
     gap
    0.14
    å¡«åħħ
    0.14
    Activations Density 0.049%

    No Known Activations