© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 31840
    Prev
    Next
    INDEX
    Explanations

    physical aspects and properties

    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
    å¢ŀåĢ¼æľįåĬ¡
    -0.10
    æĦıè¯Ĩå½¢æĢģ
    -0.09
    á»ĵng
    -0.09
    æĢ¿
    -0.09
    çIJħ
    -0.08
    å¢ŀè¿Ľ
    -0.08
    hill
    -0.08
    é»ĦçŁ³
    -0.08
    纵深
    -0.08
    ouden
    -0.08
    POSITIVE LOGITS
    physical
    0.16
     physical
    0.15
    Physical
    0.15
     Physical
    0.14
     physically
    0.13
    çī©çIJĨ
    0.12
    phys
    0.10
    å®ŀçī©
    0.10
    éĤ£ä¸ªäºº
    0.10
    身躯
    0.10
    Activations Density 0.089%

    No Known Activations