© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8054
    Prev
    Next
    INDEX
    Explanations

    creative and technical roles

    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
    olarity
    -0.09
    å®īæ£Ģ
    -0.09
    è´Ńç½®
    -0.09
    æ¯ķç«Łæĺ¯
    -0.08
     sop
    -0.08
    ç½ijè´Ń
    -0.08
    .Directory
    -0.08
    ervas
    -0.08
    _IPV
    -0.08
    çłĶ究ä¸Ńå¿ĥ
    -0.08
    POSITIVE LOGITS
    åħ¬æĬ¥
    0.08
    iquer
    0.08
    cg
    0.08
    èĤĭ
    0.08
    &R
    0.08
    illo
    0.08
     Hick
    0.08
    ×Ļ×ij
    0.08
    份
    0.08
    Animating
    0.08
    Activations Density 0.181%

    No Known Activations