© 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. 57229
    Prev
    Next
    INDEX
    Explanations

    making a choice or option

    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
    à¸Ħà¸Ńà¸Ļ
    -0.09
    å¸ĮæľĽèĥ½
    -0.09
    èįī
    -0.09
    mel
    -0.09
     Favorites
    -0.09
    ÑħоÑĤ
    -0.08
    åĭĥåĭĥ
    -0.08
    outu
    -0.08
     воп
    -0.08
     Buckingham
    -0.08
    POSITIVE LOGITS
    çļĦæľºä¼ļ
    0.13
    å®ķ
    0.11
    ä¸įåİ»
    0.10
    æľīæľºä¼ļ
    0.10
    åı¯ä»¥éĢīæĭ©
    0.10
    æľºä¼ļ
    0.09
    æĹ©çĤ¹
    0.09
    纾
    0.09
    ä¸įå½±åĵį
    0.09
    æ²ĥå°Ķ
    0.08
    Activations Density 0.035%

    No Known Activations