© 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. 63125
    Prev
    Next
    INDEX
    Explanations

    facade or exterior

    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
    ogue
    -0.09
    å¾Ģä¸Ĭ
    -0.09
    eros
    -0.09
    ç»ķ
    -0.09
    óż
    -0.09
    åıĮèĦļ
    -0.09
    æı®
    -0.09
    çĤĬ
    -0.09
    ish
    -0.09
    åºĬåŀ«
    -0.08
    POSITIVE LOGITS
    æ¡ĥèĬ±
    0.11
    å¢ī
    0.09
    æľīæĦı
    0.09
    breaker
    0.08
    å»Ĭ
    0.08
    æĦ
    0.08
    éĥĹ
    0.08
     intentional
    0.08
    åij½
    0.08
    é¾
    0.08
    Activations Density 0.020%

    No Known Activations