© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38323
    Prev
    Next
    INDEX
    Explanations

    chromosome, cell division, aging

    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
    è°ĥ
    -0.10
    æ±Łæ·®
    -0.09
    å±ŀ
    -0.08
    éĩĬ
    -0.08
     Conduct
    -0.08
    æIJŃéħį
    -0.08
    verts
    -0.08
    ion
    -0.07
    æĪIJç«ĭäºĨ
    -0.07
    èģĶ
    -0.07
    POSITIVE LOGITS
    èĮĢ
    0.12
    éĶ¦æłĩ
    0.10
    æŃ¥è¡Į
    0.09
    解å¼Ģ
    0.09
    ç½Ĺ
    0.09
    /manage
    0.09
    è¸Ĭ
    0.09
    Ã¤ÃŁ
    0.09
    éĻĢ
    0.09
    æ½¢
    0.09
    Activations Density 0.193%

    No Known Activations