© 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. 39245
    Prev
    Next
    INDEX
    Explanations

    mixed followed by another word

    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
    è£ķ
    -0.09
    ä¸Ģ声
    -0.08
    лин
    -0.08
     Roth
    -0.08
    æĶ«
    -0.08
    dob
    -0.07
    åıĺåĬ¨
    -0.07
    é³³
    -0.07
    æ´ª
    -0.07
    rette
    -0.07
    POSITIVE LOGITS
    è·ijéģĵ
    0.10
    ej
    0.10
    æĿĤ
    0.10
    ellaneous
    0.10
    åĵĢ
    0.10
    æ··åIJĪ
    0.09
    绳
    0.09
     Mixed
    0.09
    Mixed
    0.09
    åŁİ乡
    0.09
    Activations Density 0.033%

    No Known Activations