© 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. 57444
    Prev
    Next
    INDEX
    Explanations

    added daily or every

    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
    éħįä¸Ĭ
    -0.11
    çĵł
    -0.10
    èĭĮ
    -0.10
    为äºĨæĽ´å¥½
    -0.09
    зе
    -0.09
    亲çĪ±
    -0.09
    arde
    -0.09
    ä¸Ģä¸ĸ
    -0.09
    让ä»ĸ们
    -0.09
    第ä¸Ģæī¹
    -0.09
    POSITIVE LOGITS
    æ¯ı天éĥ½
    0.19
    æ¯ı天
    0.18
    æ¯ıä¸Ģ天
    0.18
    天天
    0.16
     every
    0.15
     daily
    0.14
    ë§Īëĭ¤
    0.14
    æ¯ıå¹´
    0.14
    æ¯ıæĹ¥
    0.13
    every
    0.13
    Activations Density 0.220%

    No Known Activations