© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59343
    Prev
    Next
    INDEX
    Explanations

    – or — followed by text

    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
    Negative Logits
    å®Īä½ı
    -0.10
    è¿Ļå¥Ĺ
    -0.09
    ä»Ģ麽
    -0.09
    åİŁæĿ¥çļĦ
    -0.09
    etc
    -0.09
    åĩºæĿ¥äºĨ
    -0.09
    è¿ĻèĪ¬
    -0.09
    é¡·
    -0.09
    çĵ¯
    -0.09
    rios
    -0.08
    POSITIVE LOGITS
    è¿Ļä¹Łæĺ¯
    0.08
    ä¹Łå°±æĺ¯è¯´
    0.08
    ç»Ī
    0.08
    缴èĩ³
    0.08
    å¿ĺè®°
    0.08
    ä»ħ次äºİ
    0.07
    å°¤åħ¶æĺ¯
    0.07
     part
    0.07
    å°¤åħ¶æĺ¯åľ¨
    0.07
     pencil
    0.07
    Activations Density 0.082%

    No Known Activations