© 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. 63162
    Prev
    Next
    INDEX
    Explanations

    talking about advice and lessons

    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
    äºĨä¸Ģç³»åĪĹ
    -0.10
    ä¸Ģä½ĵ
    -0.10
    æĪĸå°Ĩ
    -0.09
    æ¯ıèĤ¡
    -0.09
    为äºĨéģ¿åħį
    -0.09
    гаÑĢ
    -0.09
    ä¸įåĨįæĺ¯
    -0.09
    æľĽ
    -0.09
    åıªå¾Ĺ
    -0.09
     dys
    -0.08
    POSITIVE LOGITS
    ä¸įè¦ģ
    0.12
    æķ¬çķı
    0.11
    å§ĭç»Īä¿ĿæĮģ
    0.11
    åIJĥäºı
    0.10
    æĬĵä½ı
    0.10
    楽ãģĹ
    0.10
    åįĥä¸ĩä¸įè¦ģ
    0.10
    æŶåĪ»
    0.09
     Lá»ĭch
    0.09
    çľĭä¼¼
    0.09
    Activations Density 0.207%

    No Known Activations