© 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. 27787
    Prev
    Next
    INDEX
    Explanations

    solar energy and reactions

    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
     мил
    -0.12
    æģ¯æģ¯
    -0.09
    å®ŀäºĭæ±Ĥæĺ¯
    -0.09
     Lif
    -0.08
    éªĩ
    -0.08
    iland
    -0.08
    rado
    -0.08
    hood
    -0.08
     Flying
    -0.08
    éħį
    -0.08
    POSITIVE LOGITS
    太éĺ³èĥ½
    0.12
    çĥŃ
    0.11
    çĥŃæ°´
    0.11
    太éĺ³
    0.11
    éĺ³åħī
    0.10
    ä¿Ŀ温
    0.10
    çĥŃæ°´åĻ¨
    0.10
    Solar
    0.10
    太éĺ³åŁİ
    0.09
    æ²Ļæ¼ł
    0.09
    Activations Density 0.041%

    No Known Activations