© 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. 23728
    Prev
    Next
    INDEX
    Explanations

    negation or correction indicating wrongness

    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
    éĴĿ
    -0.10
    äºĭ项
    -0.10
     اÙĦØŃÙĬ
    -0.09
    纵
    -0.09
    缴
    -0.09
    xd
    -0.09
    æĢĿ绪
    -0.08
    èij¡èIJĦ
    -0.08
    topl
    -0.08
    cks
    -0.08
    POSITIVE LOGITS
    ç»Ŀ大å¤ļæķ°
    0.10
    ä»İä¸ļèĢħ
    0.10
    大å¤ļæķ°
    0.10
    æĪij没
    0.10
    ä»İä¸ļ
    0.09
    翼
    0.09
    漤
    0.09
    èħIJè´¥
    0.09
    ä¸Ģ个好çļĦ
    0.09
    大éĥ¨åĪĨ
    0.09
    Activations Density 0.047%

    No Known Activations