© 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. 38022
    Prev
    Next
    INDEX
    Explanations

    class inheritance and subclassing

    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
    é£İåIJ¹
    -0.09
    å¼ĢéĺĶ
    -0.08
    æĺŁçIJĥ
    -0.08
    åİĭ
    -0.08
     Hem
    -0.08
     hem
    -0.08
    è°ĥåĬ¨
    -0.08
    é©·
    -0.08
     OP
    -0.08
     MIS
    -0.07
    POSITIVE LOGITS
    继æī¿
    0.10
    __.__
    0.10
    ä¸ĭå±ŀ
    0.10
    ideshow
    0.10
    autoload
    0.10
    âĪĬ
    0.09
     живоÑĤ
    0.09
    emons
    0.09
     Choir
    0.09
    _BOTTOM
    0.09
    Activations Density 0.808%

    No Known Activations