© 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. 56372
    Prev
    Next
    INDEX
    Explanations

    energy conversion and generation

    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
    庫
    -0.11
    åºĵ
    -0.09
    lox
    -0.09
    etas
    -0.09
    åĵį
    -0.09
     luáºŃn
    -0.09
    æĢ¥äºİ
    -0.09
     SHALL
    -0.09
    åĹľ
    -0.09
    迤
    -0.09
    POSITIVE LOGITS
    èĥ½æºIJ
    0.11
    åıijçĶµ
    0.11
    åĤ¨èĵĦ
    0.11
     energy
    0.11
    èĥ½éĩı
    0.11
    太éĺ³èĥ½
    0.10
    æ¡´
    0.09
    æ·¼
    0.09
     solar
    0.09
    åĤ¨èĥ½
    0.09
    Activations Density 0.110%

    No Known Activations