© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6900
    Prev
    Next
    INDEX
    Explanations

    wearing clothes and accessories

    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
    ä¸Ģç«Ļ
    -0.10
    辫
    -0.10
    ¤
    -0.10
     backpage
    -0.09
    бав
    -0.09
     رس
    -0.09
     Phú
    -0.09
    ç®Ĺ
    -0.09
    imers
    -0.09
    yl
    -0.08
    POSITIVE LOGITS
    æĭ¯
    0.09
    itness
    0.09
    å®ļäºĨ
    0.08
    æ±Ĺ
    0.08
    çĭ¬æľīçļĦ
    0.08
    gence
    0.08
    顽强
    0.08
    dio
    0.08
    å²ij
    0.08
    å¿ĥ
    0.08
    Activations Density 0.017%

    No Known Activations