© 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. 11472
    Prev
    Next
    INDEX
    Explanations

    goji berry, aloe vera, magnesium, selenium

    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
    棣
    -0.10
    è¶ĭ
    -0.09
    ä¸įæİĴéĻ¤
    -0.09
    骧
    -0.09
     ready
    -0.09
    åĬłåī§
    -0.09
    çķĻä¸ĭäºĨ
    -0.09
    æ²ĵ
    -0.09
    å¼Ī
    -0.08
    è¶ĭäºİ
    -0.08
    POSITIVE LOGITS
    æ´ŀ
    0.11
    ç²ī
    0.09
    被èªī为
    0.09
    otec
    0.08
    æľ¬èº«å°±
    0.08
    enumerator
    0.08
    åıĹçĽĬ
    0.08
    ç»
    0.08
     packs
    0.08
    æľīçĽĬ
    0.08
    Activations Density 0.154%

    No Known Activations