© 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. 61472
    Prev
    Next
    INDEX
    Explanations

    a/an + adjective

    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
    ä¸ļ绩
    -0.09
     Certain
    -0.09
    ä¼ı
    -0.09
    åºĨ
    -0.09
    è§Ĭ
    -0.09
     Kash
    -0.08
    èĤ¡ä»·
    -0.08
    æļ´æ¶¨
    -0.08
    å½ĵæĪIJ
    -0.08
    å¡ĺ
    -0.08
    POSITIVE LOGITS
    ble
    0.10
    ç®Ĺæĺ¯
    0.10
    åĪĨå¼Ģ
    0.09
    abb
    0.09
    3
    0.09
    åı¯è°ĵæĺ¯
    0.09
    åħ¨é¢Ŀ
    0.08
     perfect
    0.08
    2
    0.08
    å§IJ妹
    0.08
    Activations Density 0.189%

    No Known Activations