© 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. 33188
    Prev
    Next
    INDEX
    Explanations

    both

    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
    ä¹Łæĺ¯ä¸Ģç§į
    -0.13
    åĩłçĤ¹
    -0.12
    åıĪèĥ½
    -0.11
    lard
    -0.11
    ä¹ŁæĪIJ为
    -0.10
    ä¹Łæĺ¯ä¸Ģ个
    -0.10
    ä¹Łè®¸
    -0.10
    ä¹Łéļıä¹ĭ
    -0.10
     возможно
    -0.10
    ä¹Łèĥ½
    -0.10
    POSITIVE LOGITS
    åIJĦèĩªçļĦ
    0.19
    åIJĦèĩª
    0.18
    ä¸įåIJĮç¨ĭ度
    0.17
    åIJĦæľī
    0.16
    åIJĮä¸Ģ个
    0.11
    åıĮåıĮ
    0.10
     respective
    0.10
    éĥ½æľīèĩªå·±
    0.10
     alike
    0.10
    对æĸ¹
    0.10
    Activations Density 0.231%

    No Known Activations