© 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. 62766
    Prev
    Next
    INDEX
    Explanations

    gridded ion thruster, constant thrust, rocket motors

    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
    龸çİĭ
    -0.09
     Giant
    -0.08
    ÙĤÙĦب
    -0.08
    ä¸Ģæł¹
    -0.08
    注æĺİæĿ¥æºIJ
    -0.08
     обÑĥÑĩ
    -0.08
    _barrier
    -0.08
    ichel
    -0.08
    ä¸Ģå®ļèĥ½
    -0.08
     Pride
    -0.08
    POSITIVE LOGITS
    常年
    0.09
    é³ĸ
    0.09
    èij«
    0.09
    สวà¸Ļ
    0.09
    èĺ¼
    0.09
    åĨ¥
    0.09
    IFA
    0.09
    æĸĩæĺĮ
    0.09
    ress
    0.09
    æľĪä¸ĭ
    0.09
    Activations Density 0.042%

    No Known Activations