© 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. 7278
    Prev
    Next
    INDEX
    Explanations

    charging, recharge, battery, sensor, removable

    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
    çĶµæºIJ
    -0.08
    ä¸įå®ļ
    -0.08
    çĩĥæĸĻ
    -0.08
    çĶµéĩı
    -0.08
    ersist
    -0.08
    å¼ĢåѦ
    -0.08
    åѵ
    -0.08
    稽
    -0.08
    çļĦçĶŁåij½
    -0.08
    éĩijå±±
    -0.08
    POSITIVE LOGITS
    éĹº
    0.10
     ÙĪÙģÙĬ
    0.09
    åIJĬ
    0.09
    Hur
    0.09
    çĨı
    0.09
    ussen
    0.09
    obic
    0.09
    ittal
    0.09
    itage
    0.09
    ixin
    0.08
    Activations Density 0.017%

    No Known Activations