© 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. 50518
    Prev
    Next
    INDEX
    Explanations

    degree or extent

    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
    æĹłæīĢ
    -0.10
    tron
    -0.08
    æĽ´åĬł
    -0.08
    éķĴ
    -0.08
     mej
    -0.08
     mim
    -0.08
    çŀ©
    -0.08
    åľĪ
    -0.08
    èijĹåIJįçļĦ
    -0.08
    è¡Į为
    -0.08
    POSITIVE LOGITS
    ç¨ĭ度
    0.20
    çļĦç¨ĭ度
    0.18
    æľīå¤ļå°ij
    0.13
    æľīå¤ļ大
    0.13
    æľī没æľī
    0.12
    ä¸İåIJ¦
    0.12
    icket
    0.11
     ìĸ¼ë§ĪëĤĺ
    0.11
    å¾Ĺä½ı
    0.11
    æĶ¯æĮģåĬĽåº¦
    0.11
    Activations Density 0.210%

    No Known Activations