© 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. 7303
    Prev
    Next
    INDEX
    Explanations

    leftover surplus

    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
    é¼»åŃIJ
    -0.10
    尽快
    -0.10
    çİ°éĺ¶æ®µ
    -0.09
    åĪ°åºķ
    -0.09
    éĻ¡
    -0.09
    éºĩ
    -0.08
    çŁ¿å±±
    -0.08
    èѬ
    -0.08
    离ä¸įå¼Ģ
    -0.08
     stat
    -0.08
    POSITIVE LOGITS
    å¤ļä½Ļ
    0.18
    å¤ļä½ĻçļĦ
    0.17
     surplus
    0.17
    åī©
    0.17
    åī©ä½Ļ
    0.17
     spare
    0.15
     leftover
    0.13
    ä½Ļ
    0.13
    åī©ä¸ĭ
    0.13
    è¿ĩåī©
    0.13
    Activations Density 0.037%

    No Known Activations