© 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. 5512
    Prev
    Next
    INDEX
    Explanations

    Aymeric, Aylan, Ayre, Ayler, Ayr

    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
    å©¿
    -0.10
    åIJĮæľŁ
    -0.10
    edException
    -0.10
    æĭ¯
    -0.10
    æį§
    -0.09
    agem
    -0.09
    eren
    -0.09
    ouver
    -0.09
    ç¼Ĥ
    -0.09
    Ħ
    -0.09
    POSITIVE LOGITS
    itte
    0.10
    ä¸įäºĨ
    0.10
    relude
    0.09
    itud
    0.09
    eer
    0.09
    itary
    0.09
    urved
    0.09
    	TokenName
    0.08
    lobs
    0.08
    utenberg
    0.08
    Activations Density 0.008%

    No Known Activations