© 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. 24047
    Prev
    Next
    INDEX
    Explanations

    deciding or choice

    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
    æµģéĢļ
    -0.09
    abl
    -0.09
    ä¸ŃéĢĶ
    -0.09
    èĥĮåIJİ
    -0.08
    exas
    -0.08
     Pole
    -0.08
     Hi
    -0.08
    å¹ķåIJİ
    -0.08
    est
    -0.07
    沿
    -0.07
    POSITIVE LOGITS
    åĨ³å®ļ
    0.12
     quyết
    0.10
    éĻŁ
    0.10
    ä¸įæĸŃå®ĮåĸĦ
    0.10
    åĪ¥äºº
    0.10
     deciding
    0.10
    .dismiss
    0.10
    æ¯ı个人çļĦ
    0.10
     décision
    0.10
    ä¹Łåıªèĥ½
    0.10
    Activations Density 0.024%

    No Known Activations