© 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. 5154
    Prev
    Next
    INDEX
    Explanations

    publisher names

    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
     superst
    -0.09
    imeType
    -0.09
    à¸Ķาว
    -0.08
    etz
    -0.08
    容
    -0.08
    ç»Ħéķ¿
    -0.08
     GIVEN
    -0.08
    ute
    -0.08
    ica
    -0.08
    åģľçīĮ
    -0.08
    POSITIVE LOGITS
    社
    0.12
    åĩºçīĪ
    0.11
     Publishers
    0.10
    è£ĺ
    0.10
    æĪIJé¾Ļ
    0.10
    åĩºçīĪ社
    0.10
    åij¨åĪĬ
    0.09
    è¿Ļåĩłä¸ª
    0.09
     изд
    0.09
     publishing
    0.09
    Activations Density 0.028%

    No Known Activations