© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6100
    Prev
    Next
    INDEX
    Explanations

    communication systems

    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
    Negative Logits
    icide
    -0.09
    解åĨ³éĹ®é¢ĺ
    -0.09
    横åIJij
    -0.09
    _sd
    -0.09
    _uid
    -0.09
    èĤ¯
    -0.09
    uid
    -0.08
    oda
    -0.08
    UID
    -0.08
     liberal
    -0.08
    POSITIVE LOGITS
    ä½ľåĿĬ
    0.10
    ä¸Ģç«Ļ
    0.10
    ä¸ĢéĶ®
    0.10
    _UNDEFINED
    0.09
    aminer
    0.09
    enstein
    0.09
    æĹłéľĢ
    0.09
    æ£ķèī²
    0.09
    为ä¼ģä¸ļ
    0.09
    èį¯ä¸ļ
    0.09
    Activations Density 0.100%

    No Known Activations