© 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. 4677
    Prev
    Next
    INDEX
    Explanations

    distribution or directory contents

    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
    alls
    -0.08
    4
    -0.08
    ily
    -0.08
    ÑĩеÑģÑĤво
    -0.08
    à¸ļรร
    -0.08
    æľŁ
    -0.08
    irm
    -0.08
    cly
    -0.07
    atile
    -0.07
     tractor
    -0.07
    POSITIVE LOGITS
    éĤ£è¾¹
    0.11
    æľīæĽ´å¤ļçļĦ
    0.10
     fanc
    0.10
    .axes
    0.09
    å¯Ħ
    0.09
    ä¼ļè®®ä¸Ĭ
    0.09
    éĤ¬
    0.09
    ä¸Ĭæĸ¹
    0.08
    dong
    0.08
    etailed
    0.08
    Activations Density 0.223%

    No Known Activations