© 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. 58716
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and symbols

    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
    ä¸Ģ件
    -0.09
    åĨħå¿ĥçļĦ
    -0.08
    åĥŃ
    -0.08
    æĦŁ
    -0.08
    pls
    -0.08
    ä¸Ģ件äºĭ
    -0.08
    è§ģè¯Ĩ
    -0.08
     Pik
    -0.08
     contrary
    -0.08
    ÑĢай
    -0.08
    POSITIVE LOGITS
    æĹģ
    0.10
    è©
    0.09
    人士
    0.09
    ä¸Ģç»ı
    0.09
    UNIX
    0.09
    è¡Ķ
    0.09
    éĹªéĹª
    0.09
    æİĪ
    0.09
    æľīäºĽäºº
    0.09
     piv
    0.08
    Activations Density 0.086%

    No Known Activations