© 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. 33412
    Prev
    Next
    INDEX
    Explanations

    language training and skills

    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
    æļĸ
    -0.09
    ä¸Ģ次次
    -0.08
     homework
    -0.08
    è¿Ļ个è¯į
    -0.08
     AD
    -0.08
    åīįçŀ»
    -0.08
    ä½ĵåĬĽ
    -0.08
    åī¡
    -0.08
    throp
    -0.08
    perm
    -0.07
    POSITIVE LOGITS
     languages
    0.12
    å¤ĸåĽ½è¯Ń
    0.12
    å¤ĸè¯Ń
    0.11
    Ế
    0.11
    languages
    0.10
     foreign
    0.10
    åĬ¨æ¼«
    0.10
     Languages
    0.10
    åIJĦæł·
    0.10
    foreign
    0.09
    Activations Density 0.053%

    No Known Activations