© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38492
    Prev
    Next
    INDEX
    Explanations

    pour/in/flowing/comes

    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
     itemprop
    -0.10
     khá»ıi
    -0.09
    tery
    -0.09
    åħ¨ç¨ĭ
    -0.09
    ogo
    -0.09
    æݧèĤ¡éĽĨåĽ¢
    -0.09
    ç³»åĪĹæ´»åĬ¨
    -0.09
    unden
    -0.09
     ADS
    -0.08
     hen
    -0.08
    POSITIVE LOGITS
    è¿ĽæĿ¥
    0.11
    æĿ¥ä¸´
    0.11
    æĿ¥çļĦ
    0.11
    秣éĩij
    0.10
    é¢Ĩ
    0.10
    éłĺ
    0.10
    é½IJ
    0.10
    åĵį
    0.10
    parable
    0.09
    ä¸ĭæĿ¥çļĦ
    0.09
    Activations Density 0.036%

    No Known Activations