© 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. 11709
    Prev
    Next
    INDEX
    Explanations

    award or recognition

    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¶Ĭæĺ¯
    -0.10
    å¼ĢéĺĶ
    -0.09
    æľªç»ı
    -0.09
    å·²ä¹ħçļĦ
    -0.09
    åħ¬çĽĬ
    -0.09
    羣åģĩ
    -0.09
    äºīåıĸ
    -0.08
    ÙĬÙĪ
    -0.08
    ULER
    -0.08
    oe
    -0.08
    POSITIVE LOGITS
    çĶļèĩ³
    0.12
    åݦ
    0.11
    çĶļèĩ³è¿ĺ
    0.10
    æı
    0.10
    å¹´ä¹ĭ
    0.10
    å¹´ä¹ĭä¹ħ
    0.09
    åİŁè°ħ
    0.09
    inst
    0.09
    å¸Ĥåľºä»½é¢Ŀ
    0.09
    溢价
    0.09
    Activations Density 0.049%

    No Known Activations