© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16913
    Prev
    Next
    INDEX
    Explanations

    commands followed by nouns

    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
    娩
    -0.10
    sz
    -0.09
    assy
    -0.09
    å¢Ł
    -0.09
    ÄĽ
    -0.09
    лиÑĩ
    -0.09
    管çIJĨå±Ģ
    -0.09
    inn
    -0.09
    å¿Ļ
    -0.09
    ķ
    -0.09
    POSITIVE LOGITS
    able
    0.15
    ä¸įäºĨ
    0.13
    äºĨ许å¤ļ
    0.13
    åĴĮå®ĮåĸĦ
    0.13
    äºĨä¸įå°ij
    0.13
    äºĨå¾Īå¤ļ
    0.13
    äºĨä¸Ģ个
    0.12
    äºĨä¸Ģæī¹
    0.11
    äºĨä¸Ģ
    0.11
    äºĨ个
    0.10
    Activations Density 0.617%

    No Known Activations