© 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. 3493
    Prev
    Next
    INDEX
    Explanations

    sensing and feeling

    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
    æĦĪ
    -0.14
    ãĤĴ缮æĮĩ
    -0.10
    èIJ¥ä¸ļé¢Ŀ
    -0.10
    egrity
    -0.10
    鲧
    -0.10
    åĺī宾
    -0.10
    çļĦåľ°åĽ¾
    -0.10
    .Ui
    -0.09
    servers
    -0.09
    éķŃ
    -0.09
    POSITIVE LOGITS
    触æij¸
    0.11
     touch
    0.09
    触
    0.09
    æĮĩå°ĸ
    0.09
    8
    0.08
    å®ĺ
    0.08
    æij¸
    0.08
    æį®æѤ
    0.08
     fat
    0.08
    7
    0.08
    Activations Density 0.028%

    No Known Activations