© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20673
    Prev
    Next
    INDEX
    Explanations

    redundancy or redundant

    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
    絡
    -0.10
    æīĭä¸ŃçļĦ
    -0.10
    åĪ«
    -0.09
    issy
    -0.09
    并åIJij
    -0.08
    è£
    -0.08
    æŀª
    -0.08
    认æ¸ħ
    -0.08
    éĽªèĬ±
    -0.08
    讪
    -0.08
    POSITIVE LOGITS
    åĨĹ
    0.20
     redund
    0.17
     redundant
    0.17
     redundancy
    0.16
    éĩįå¤į
    0.12
    å¤ļä½Ļ
    0.11
    èµĺ
    0.11
    å¤ļéĩį
    0.10
    alis
    0.10
    Kal
    0.09
    Activations Density 0.050%

    No Known Activations