© 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. 32420
    Prev
    Next
    INDEX
    Explanations

    changes and variations

    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
    饮
    -0.10
    çħ¦
    -0.09
    æ¯įæł¡
    -0.09
    Expose
    -0.09
    WE
    -0.08
     gió
    -0.08
    ç¥Ī
    -0.08
    zell
    -0.08
    æľīæĦıä¹ī
    -0.08
    åĬª
    -0.08
    POSITIVE LOGITS
    ç½®æį¢
    0.10
     variations
    0.10
    ä¸įå°½
    0.09
    åĩºåħ¥
    0.09
     ingredients
    0.09
     additions
    0.09
    à¹Ģ
    0.09
     addition
    0.09
    omal
    0.09
    erate
    0.09
    Activations Density 0.027%

    No Known Activations