© 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. 37588
    Prev
    Next
    INDEX
    Explanations

    either or

    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»»ä½ķ
    -0.14
    ä»»ä½ķä¸Ģ个
    -0.13
     any
    -0.11
    ä»»ä½ķ人éĥ½
    -0.10
    ä»»ä½ķ人
    -0.10
    ä»»ä½ķæŶåĢĻ
    -0.10
    ä¹Łæĺ¯ä¸Ģ个
    -0.09
     ANY
    -0.09
    ANY
    -0.09
    any
    -0.08
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.19
     Either
    0.12
    either
    0.12
     either
    0.11
    Either
    0.11
    å¹²èĦĨ
    0.11
    ä¸įåIJĮç¨ĭ度
    0.10
    åIJĦç§įåIJĦæł·
    0.10
    侨
    0.10
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.10
    Activations Density 0.276%

    No Known Activations