© 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. 54545
    Prev
    Next
    INDEX
    Explanations

    organization and partnership

    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
    人们
    -0.10
    人们çļĦ
    -0.09
    ruise
    -0.08
    åħĪçĶŁ
    -0.08
    éĥµ
    -0.08
    еÑģÑĤи
    -0.08
     ÙĦدÙī
    -0.08
    /bower
    -0.08
    è¿Ļ让
    -0.08
    _partitions
    -0.08
    POSITIVE LOGITS
    ä»ĸä»¬åľ¨
    0.19
    ä»ĸ们
    0.18
    对ä»ĸ们
    0.16
    ä»ĸ们çļĦ
    0.15
    ç»Ļä»ĸ们
    0.15
    让ä»ĸ们
    0.14
    ä»ĸåĢij
    0.14
     their
    0.13
    æĺ¯ä»ĸ
    0.13
    å½¼ãĤī
    0.13
    Activations Density 0.508%

    No Known Activations