© 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. 22109
    Prev
    Next
    INDEX
    Explanations

    actor 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
     alone
    -0.10
    éĤ£è¾¹
    -0.09
    uits
    -0.09
    åIJĮäºĭ们
    -0.08
    åIJĦçķĮ
    -0.08
     Alone
    -0.08
    åħļå§Ķ
    -0.08
     VERIFY
    -0.08
     ÙħØŃÙħ
    -0.08
    奢ä¾Ī
    -0.08
    POSITIVE LOGITS
    ä¸Ģè§Ĵ
    0.13
     ÑĢоли
    0.10
    è§Ĵèī²
    0.10
    å½¹
    0.10
    çļĦè§Ĵèī²
    0.09
     Ñģобой
    0.09
    è¯įæĿ¡
    0.09
    -role
    0.09
    游æĪıè§Ĵèī²
    0.08
    inals
    0.08
    Activations Density 0.073%

    No Known Activations