© 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. 10970
    Prev
    Next
    INDEX
    Explanations

    light bulbs and lighting

    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
    ThreadId
    -0.09
    دÙģاع
    -0.09
    çıŃ
    -0.09
    éħį
    -0.09
    ahn
    -0.09
    æ³ķå®ļ
    -0.09
    cta
    -0.08
    aldi
    -0.08
    åĽŀé¦Ī
    -0.08
    æĮ¹
    -0.08
    POSITIVE LOGITS
     bulb
    0.10
    bul
    0.10
    ä¸Ńåħ³
    0.10
    ç»ıåķĨ
    0.10
    çģ¯åħ·
    0.10
    éķ¿å¯¿
    0.09
    uled
    0.09
    çģ¯
    0.09
     bulbs
    0.08
    寿åij½
    0.08
    Activations Density 0.047%

    No Known Activations