© 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. 18258
    Prev
    Next
    INDEX
    Explanations

    end of list/code block

    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
    æĪĸèĢħ说
    -0.10
    ä¹Łå¥½
    -0.09
    é¦ĸåħĪæĺ¯
    -0.09
    é¦ĸåħĪ
    -0.09
     bare
    -0.09
    gos
    -0.08
    Include
    -0.08
     Include
    -0.08
    å°±è·Ł
    -0.08
    LAY
    -0.08
    POSITIVE LOGITS
    è¿ĻäºĽéĥ½æĺ¯
    0.20
    è¿Ļä¸ĢåĪĩ
    0.16
    æĢ»ä¹ĭ
    0.16
    çŃīçŃī
    0.13
    æĢ»èĢĮè¨Ģä¹ĭ
    0.13
    éĥ½æľīçĿĢ
    0.11
    éĥ½æĺ¯éĿŀ常
    0.10
    æĹłä¸į
    0.10
    æĢ»çļĦæĿ¥è¯´
    0.10
     importantly
    0.10
    Activations Density 0.239%

    No Known Activations