© 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. 17017
    Prev
    Next
    INDEX
    Explanations

    leftover or excess

    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
    èѬ
    -0.10
    椽
    -0.09
    ä¸į该
    -0.09
    æŃ£å¸¸ä½¿çĶ¨
    -0.09
    å°¼æĸ¯
    -0.09
    èŁij
    -0.09
    ç¬ŀ
    -0.09
    åķ§
    -0.09
    èµ·æŃ¥
    -0.09
    è¡
    -0.09
    POSITIVE LOGITS
     surplus
    0.11
    è¿ĩåī©
    0.11
     excess
    0.11
    å¤ļä½ĻçļĦ
    0.10
     leftover
    0.09
    UTIL
    0.09
     dÆ°
    0.09
    éĹ²ç½®
    0.09
    Util
    0.09
    ose
    0.09
    Activations Density 0.032%

    No Known Activations