© 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. 3968
    Prev
    Next
    INDEX
    Explanations

    seen as

    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
    åıĻäºĭ
    -0.09
    è°ģçŁ¥éģĵ
    -0.08
    ä¸İä¼Ĺä¸įåIJĮ
    -0.08
    æĭ¨
    -0.08
     Cer
    -0.08
    åĽłä¸ºä½ł
    -0.08
    çŃ
    -0.08
    诸
    -0.08
    it
    -0.08
    æī¿è®¤
    -0.08
    POSITIVE LOGITS
    è§Ĩ为
    0.17
    è¦ĸçĤº
    0.12
    解读
    0.11
    被è§Ĩ为
    0.11
    å½ĵæĪIJ
    0.10
    å½ĵä½ľ
    0.10
    认为
    0.10
    è§Ĩ
    0.10
    æ±ľ
    0.10
    aken
    0.10
    Activations Density 0.078%

    No Known Activations