© 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. 32385
    Prev
    Next
    INDEX
    Explanations

    optional but necessary

    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
    ilo
    -0.08
    绳
    -0.08
    æĬĹè¡¡
    -0.08
    æı´
    -0.08
    綾
    -0.08
    æŀIJ
    -0.08
     piv
    -0.08
    è¿Ľåįļä¼ļ
    -0.07
    ill
    -0.07
    è¿ĩåİ»çļĦ
    -0.07
    POSITIVE LOGITS
    ä¹Łåı¯
    0.13
    ä¹Łåı¯ä»¥
    0.13
    è¿Ļä¹Īåģļ
    0.12
    å¿ħè¦ģ
    0.12
    ä¸įå¿ħ
    0.12
    没æľīå¿ħè¦ģ
    0.11
     unnecessary
    0.11
    没å¿ħè¦ģ
    0.11
    å¦Ĥæŀľä½łæĥ³
    0.10
    è¿Ļæł·åģļ
    0.10
    Activations Density 0.092%

    No Known Activations