© 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. 39780
    Prev
    Next
    INDEX
    Explanations

    seems to be able

    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
    æĪijçŁ¥éģĵ
    -0.11
    æĪijçĽ¸ä¿¡
    -0.10
     извеÑģÑĤ
    -0.09
    亿ä¸ĩ
    -0.09
    ZERO
    -0.09
     reportedly
    -0.09
     Pett
    -0.08
    æĪij认为
    -0.08
     przecież
    -0.08
     natürlich
    -0.08
    POSITIVE LOGITS
    æŃ¤äºº
    0.10
     quite
    0.10
    å¾Īåĸľæ¬¢
    0.10
    ä¼¼ä¹İæĺ¯
    0.10
    ä¸įå°ij
    0.09
    ä¸į太
    0.09
    èŀį为ä¸Ģä½ĵ
    0.09
    izzie
    0.09
    é¢ĩ为
    0.09
    ä¸įéĶĻçļĦ
    0.08
    Activations Density 0.213%

    No Known Activations