© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10052
    Prev
    Next
    INDEX
    Explanations

    academic disciplines and research

    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¸Ģå°ģ
    -0.09
    æĹĭ
    -0.09
    ä¸ĢæľŁ
    -0.09
    ä¸Ģ大åłĨ
    -0.09
    äºĮæľŁ
    -0.08
    漩
    -0.08
     hé
    -0.08
    ç»ıèIJ¥èĢħ
    -0.08
    å¿ĥå¾Ĺ
    -0.08
    æĻģ
    -0.08
    POSITIVE LOGITS
    Ã¼ÃŁ
    0.09
    lbrace
    0.08
    .jet
    0.08
    bish
    0.08
     Treaty
    0.07
     Dialog
    0.07
    åľŃ
    0.07
     Shelf
    0.07
     primaries
    0.07
    .datab
    0.07
    Activations Density 0.085%

    No Known Activations