© 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. 26727
    Prev
    Next
    INDEX
    Explanations

    stars and star formation

    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
    ä¾µ
    -0.11
    éľ¾
    -0.10
    人åĿĩ
    -0.10
    eway
    -0.09
    æĭĴ
    -0.09
    è¯ı
    -0.09
    çŁ¢
    -0.09
     press
    -0.09
    èĨĪ
    -0.09
    éĻĮçĶŁäºº
    -0.08
    POSITIVE LOGITS
    åIJĮåѦ们
    0.10
    ä½ij
    0.09
    æĺ¨
    0.08
    æĻ¤
    0.08
    èĪįå¾Ĺ
    0.08
    ì§ij
    0.08
    /lg
    0.08
    arding
    0.08
    hus
    0.08
    .transition
    0.07
    Activations Density 0.111%

    No Known Activations