© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 3546
    Prev
    Next
    INDEX
    Explanations

    actor or actress

    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
    ä½ļ
    -0.09
    åIJĥ饱
    -0.09
    chaft
    -0.09
     ArrayBuffer
    -0.09
    ream
    -0.09
    _finalize
    -0.09
    è¾¾æłĩ
    -0.09
    _ORIGIN
    -0.08
    æĥ³è±¡åĬĽ
    -0.08
    _verification
    -0.08
    POSITIVE LOGITS
    主æ¼Ķ
    0.10
    夫人
    0.10
    çijŀ士
    0.09
     acting
    0.09
    度åģĩ
    0.09
    æī®
    0.08
     knights
    0.08
    饰æ¼Ķ
    0.08
     Oscar
    0.08
     Tour
    0.08
    Activations Density 0.101%

    No Known Activations