© 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. 57420
    Prev
    Next
    INDEX
    Explanations

    iron, water, canals, railways

    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
    ovich
    -0.09
    æŀIJ
    -0.09
    _MOUNT
    -0.09
    æµ·å¤ĸ
    -0.08
    ç½®ä¸ļ
    -0.08
    åĽ½éĻħå¸Ĥåľº
    -0.08
     Meyer
    -0.08
    ä¾ĭè¡Į
    -0.08
    less
    -0.08
     beaches
    -0.08
    POSITIVE LOGITS
    åĦĴ
    0.11
    å·¥åĮł
    0.10
    çģµéŃĤ
    0.09
    åı²æĸĻ
    0.09
    çĶŁæ´»ä¹łæĥ¯
    0.09
    çļĦçģµéŃĤ
    0.09
    溯
    0.09
    欢快
    0.08
    åŁĤ
    0.08
    ä¸Ģ段
    0.08
    Activations Density 0.141%

    No Known Activations