© 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. 54050
    Prev
    Next
    INDEX
    Explanations

    fuel and its applications

    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
    衬
    -0.10
    ç£ķ
    -0.10
    ä¸Ģ线
    -0.09
    åĨ·æ°´
    -0.09
     клÑĥб
    -0.09
    ÑĤен
    -0.09
    åĮĹ大
    -0.09
    åĿĩä»·
    -0.09
    åıĹ访èĢħ
    -0.09
    itä
    -0.09
    POSITIVE LOGITS
    çĩĥæĸĻ
    0.09
     anticip
    0.09
    èģĮåĬ¡
    0.09
     Tir
    0.08
    ä¸įåı¯æĢĿ
    0.08
     Vog
    0.08
    丧
    0.08
    леж
    0.08
    åĴĮä»ĸçļĦ
    0.08
    ÑĥÑī
    0.08
    Activations Density 0.031%

    No Known Activations