© 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. 49300
    Prev
    Next
    INDEX
    Explanations

    communication and calls

    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¸ĢåĪĨéĴ±
    -0.09
    æīĭç»Ńè´¹
    -0.09
    agnost
    -0.09
    ifer
    -0.08
    æĢ§å¼º
    -0.08
    èī¯å¿ĥ
    -0.08
    åIJ¯èĴĻ
    -0.08
    çķľ
    -0.08
    æĭ¯
    -0.08
     Lagos
    -0.08
    POSITIVE LOGITS
    ç»ĵæĿŁåIJİ
    0.11
    è·¨åĽ½
    0.09
    å¤ļä¸ªåĽ½å®¶
    0.09
     اÙĦسÙħ
    0.09
    ç¯
    0.09
    åIJ¹
    0.08
    CES
    0.08
    มาà¸Īาà¸ģ
    0.08
    æĦŁè§¦
    0.08
     Reign
    0.08
    Activations Density 0.011%

    No Known Activations