© 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. 18845
    Prev
    Next
    INDEX
    Explanations

    should / supposed to

    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
    åIJĦä½į
    -0.11
    èµĦæºIJä¼ĺåĬ¿
    -0.10
    æĺ¯ä¸ŃåĽ½
    -0.10
    太快
    -0.10
    æĺ¯æĪijåĽ½
    -0.10
    å·²æĺ¯
    -0.09
    ç¿ł
    -0.09
    _INSERT
    -0.09
    è¿Ļæĺ¯åĽłä¸º
    -0.09
    éĶ¦ç»£
    -0.09
    POSITIVE LOGITS
    åºĶ该æĺ¯
    0.13
    åºĶæľīçļĦ
    0.11
     supposed
    0.10
     shouldBe
    0.10
    å°±åºĶ该
    0.09
    åºĶ该
    0.09
    олж
    0.09
    åºĶå½ĵ
    0.09
    åĹħ
    0.09
    æķĽ
    0.09
    Activations Density 0.107%

    No Known Activations