© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50785
    Prev
    Next
    INDEX
    Explanations

    green technologies, energy efficiency, water usage

    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
    èIJ¥åķĨ
    -0.10
     repro
    -0.09
     Pist
    -0.09
    çĻ¾åIJĪ
    -0.09
    asil
    -0.08
    аÑĢÑĮ
    -0.08
    åĿŀ
    -0.08
     Musk
    -0.08
    空çĻ½
    -0.08
    èݺ
    -0.08
    POSITIVE LOGITS
    诣
    0.10
    åĩ¡
    0.09
    åħ¨åijĺ
    0.09
    ä¼łéĢĴ
    0.09
    交åıĭ
    0.09
    å°½åĬĽ
    0.08
    åįĢåŁŁ
    0.08
    oyal
    0.08
    åłĤ
    0.08
    enen
    0.08
    Activations Density 0.061%

    No Known Activations