© 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. 58224
    Prev
    Next
    INDEX
    Explanations

    while contrasting statements

    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
    è¦ģä¹Ī
    -0.11
    好åIJĹ
    -0.10
    ually
    -0.10
    åħ¶æ¬¡æĺ¯
    -0.10
    ä»Ģä¹Īåij¢
    -0.09
    äºĽä»Ģä¹Ī
    -0.09
    èĢĮä¸Ķ
    -0.09
     gì
    -0.09
    cul
    -0.09
    佬
    -0.09
    POSITIVE LOGITS
    大å¤ļæķ°
    0.10
    è¿ľå¤Ħ
    0.09
    ä¸į太
    0.09
    æĦıä¹īä¸Ĭ
    0.09
    bury
    0.09
    å¤ļãģıãģ®
    0.08
    ä¼Ĺå¤ļ
    0.08
    Ø«ÙĨ
    0.08
    å¤ļæķ°
    0.08
    clause
    0.08
    Activations Density 0.021%

    No Known Activations