© 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. 26970
    Prev
    Next
    INDEX
    Explanations

    awards and professional organizations

    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
    æĻ®åıĬ
    -0.10
    羣缸
    -0.10
    /wiki
    -0.09
    ç»ijå®ļ
    -0.09
    hone
    -0.09
    åĨįå¤ļ
    -0.09
    å¥
    -0.08
    áŀł
    -0.08
    åIJĦåľ°
    -0.08
    两æīĭ
    -0.08
    POSITIVE LOGITS
    éĻįåĪ°
    0.09
    çIJ¥
    0.08
    åģĥ
    0.08
    ä¸ĸçķĮ第ä¸Ģ
    0.08
    dden
    0.08
    еÑģÑĤво
    0.08
    ä»Ĭ天çļĦ
    0.07
    ECT
    0.07
    _Format
    0.07
    ambia
    0.07
    Activations Density 0.025%

    No Known Activations