© 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. 30099
    Prev
    Next
    INDEX
    Explanations

    all backgrounds and demographics

    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
    æµģ转
    -0.10
    åijĹ
    -0.09
    ENU
    -0.09
    åįģ足
    -0.09
    èĦ±
    -0.09
    æ¦ľ
    -0.09
    èĦ«
    -0.08
     Ori
    -0.08
    è¿Ļç±»
    -0.08
    éķ¿è¿ľ
    -0.08
    POSITIVE LOGITS
    èĥĮæĻ¯
    0.11
    shield
    0.11
     backgrounds
    0.11
    æĪª
    0.10
    注æĺİæĿ¥æºIJ
    0.10
    shade
    0.09
    å¹´é¾Ħ
    0.09
     nationality
    0.09
    èŃĺ
    0.09
     background
    0.08
    Activations Density 0.043%

    No Known Activations