© 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. 54718
    Prev
    Next
    INDEX
    Explanations

    take or took

    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
    kte
    -0.10
    ä¸Ģ头
    -0.09
    ç»ķ
    -0.09
    符
    -0.09
    æŃ£éĿ¢
    -0.09
    å¿ĥæĦı
    -0.08
    ç²²
    -0.08
     FN
    -0.08
    汶
    -0.08
    æ°ª
    -0.08
    POSITIVE LOGITS
    ä¾
    0.10
    äºīåıĸ
    0.09
    able
    0.09
    bots
    0.09
    å¼ĢæºIJ
    0.08
     ÐŀÑĩ
    0.08
    豸
    0.08
    ä¸ĭåİ»
    0.08
    hev
    0.08
    ants
    0.08
    Activations Density 0.026%

    No Known Activations