© 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. 30108
    Prev
    Next
    INDEX
    Explanations

    isle, audible, or place names ending in -land

    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¯Ħæīĺ
    -0.13
    éĻĮ
    -0.10
    åħ¨èĥ½
    -0.09
    é¢Ĩ导干éĥ¨
    -0.09
    åµĺ
    -0.09
    วาà¸ĩ
    -0.09
    _GB
    -0.09
     اÙĦجÙħÙĩ
    -0.09
    رع
    -0.09
    å©
    -0.09
    POSITIVE LOGITS
    ä¸Ģç§Ĵ
    0.09
    ivant
    0.09
    ijken
    0.09
    佬
    0.09
    便ä¼ļ
    0.08
    ä¸įåħĭ
    0.08
    inic
    0.07
    æį
    0.07
    åĵ½
    0.07
    hart
    0.07
    Activations Density 0.001%

    No Known Activations