© 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. 37273
    Prev
    Next
    INDEX
    Explanations

    organizational entities and their roles

    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
    çļĦå¢ŀéķ¿
    -0.09
     yourselves
    -0.09
     Miner
    -0.09
    виз
    -0.09
    ãĤ¶
    -0.09
    .Initialize
    -0.09
    ivor
    -0.09
    hoc
    -0.08
    æľīæĦıä¹ī
    -0.08
    åħ¬åı¸ç«łç¨ĭ
    -0.08
    POSITIVE LOGITS
    wide
    0.10
    级以ä¸Ĭ
    0.09
    ees
    0.09
    æĮ£
    0.08
    à¹Ħหà¸Ļ
    0.08
    åIJĦé¡¹å·¥ä½ľ
    0.08
    èĩ³æѤ
    0.08
     Huff
    0.08
    bei
    0.08
    éĢĶä¸Ń
    0.08
    Activations Density 0.086%

    No Known Activations