© 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. 3568
    Prev
    Next
    INDEX
    Explanations

    beginning, end, or continuation

    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
    åĥĸ
    -0.10
    ç²®
    -0.09
     igen
    -0.09
    åªļ
    -0.09
    纶
    -0.08
    é»ij
    -0.08
    iling
    -0.08
    ä¹Łæĺ¯å¦ĤæѤ
    -0.08
    èıľ
    -0.08
    éļ¾æĢª
    -0.08
    POSITIVE LOGITS
    è¿ĺè¦ģ
    0.10
    è¿ĺå¾Ĺ
    0.10
    éĤĦæľī
    0.10
    è¿ĺéľĢè¦ģ
    0.10
     yet
    0.10
    éĤĦè¦ģ
    0.10
    ä»įæľª
    0.09
    æĽľ
    0.09
    è¿ĺéľĢ
    0.09
    .backend
    0.09
    Activations Density 0.033%

    No Known Activations