© 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. 20296
    Prev
    Next
    INDEX
    Explanations

    aware of

    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
    ãĢĤï¼Į
    -0.09
    漪
    -0.08
    è¡¢
    -0.08
    icer
    -0.08
    íķij
    -0.08
    èįı
    -0.08
    顼
    -0.08
    çļĦçħ§çīĩ
    -0.08
    æĨ¬
    -0.08
    æĪIJ为äºĨ
    -0.08
    POSITIVE LOGITS
    нÑıÑĤ
    0.09
     sake
    0.09
    -del
    0.09
    åĬĿ
    0.08
    代
    0.08
    setter
    0.08
    æ·±åħ¥äººå¿ĥ
    0.08
    èij¬
    0.08
    æĦıä¹ī
    0.08
     fart
    0.08
    Activations Density 0.188%

    No Known Activations