© 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. 19997
    Prev
    Next
    INDEX
    Explanations

    lip service, token hunger, through life

    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
    inte
    -0.09
    èµĦæºIJéħįç½®
    -0.09
    ä¸Ģè§Ī
    -0.09
    æļ´
    -0.09
    ASC
    -0.09
    èĭij
    -0.08
     esc
    -0.08
    é»Ŀ
    -0.08
    ·»
    -0.08
    æµģåĬ¨
    -0.08
    POSITIVE LOGITS
    å½¢å¼ı
    0.16
    èµ°è¿ĩ
    0.15
    æķ·
    0.14
     formal
    0.12
    çļĦå½¢å¼ı
    0.12
    ä¾ĭè¡Į
    0.11
    æīĭç»Ń
    0.11
    å¤ĸ表
    0.11
     Lip
    0.11
     lip
    0.11
    Activations Density 0.054%

    No Known Activations