© 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. 965
    Prev
    Next
    INDEX
    Explanations

    interior design

    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
    帽åŃIJ
    -0.09
    çĥŁèĬ±
    -0.09
    èĤ©
    -0.09
    shima
    -0.08
    åħ¬çĽĬ
    -0.08
    姿åĬ¿
    -0.08
    /meta
    -0.08
    ä¾ĽéľĢ
    -0.08
    éģĩ
    -0.08
    èī°
    -0.08
    POSITIVE LOGITS
    客åİħ
    0.15
    è£ħä¿®
    0.15
    å¸ĥç½®
    0.14
    家å±ħ
    0.13
    å±ħ室
    0.13
     interior
    0.13
    çļĦ设计
    0.12
    设计æĸ¹æ¡Ī
    0.12
    设计
    0.12
    é£İæ°´
    0.12
    Activations Density 0.147%

    No Known Activations