© 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. 61908
    Prev
    Next
    INDEX
    Explanations

    explaining absence of something

    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
    èIJ¥ä¸ļ
    -0.09
    ToObject
    -0.09
    æĪij说
    -0.08
    benchmark
    -0.08
     impress
    -0.08
    achi
    -0.08
    åIJİæĤĶ
    -0.08
    没人
    -0.08
    YPD
    -0.08
    .REG
    -0.08
    POSITIVE LOGITS
    è¦ģç´§
    0.10
    ൽ
    0.10
    æĽ´éĩįè¦ģçļĦ
    0.09
     пÑĢазд
    0.09
    å¿Ļç¢Į
    0.09
     занÑıÑĤ
    0.09
    åij¨è½¬
    0.09
    责任ç¼ĸè¾ij
    0.09
    é£İåı£
    0.09
    åĪ«çļĦ
    0.09
    Activations Density 0.125%

    No Known Activations