© 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. 55918
    Prev
    Next
    INDEX
    Explanations

    school/class events

    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
     pq
    -0.09
    ovich
    -0.08
     ·
    -0.08
    icom
    -0.08
    ä¸Ŀ绸ä¹ĭè·¯
    -0.08
    ·
    -0.07
     Bloom
    -0.07
    rn
    -0.07
    ç²¹
    -0.07
    å¤ĩæ¡Ī
    -0.07
    POSITIVE LOGITS
    çıŃ级
    0.17
    çıŃ主任
    0.16
    çıŃ
    0.14
    èµ°å»Ĭ
    0.12
    éĽĨä½ĵ
    0.12
    å¹¼ç¨ļ
    0.11
    æ¯ķä¸ļ
    0.11
    æķĻ室
    0.11
    çıŃéķ¿
    0.11
    è¿ŁåĪ°
    0.11
    Activations Density 0.056%

    No Known Activations