© 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. 55378
    Prev
    Next
    INDEX
    Explanations

    limits and quantities

    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
    æ®ĸ
    -0.10
    宿
    -0.10
    æŁĦ
    -0.09
    çĤ¹å¤ļ
    -0.09
    å¾Īéĩįè¦ģçļĦ
    -0.09
     ÑĢа
    -0.09
    çĶļèĩ³è¿ĺ
    -0.09
    大å®Ĺ
    -0.09
    suit
    -0.08
     акÑĤÑĥ
    -0.08
    POSITIVE LOGITS
    ä¸įè¶ħè¿ĩ
    0.15
    ä¸įå¾Ĺè¶ħè¿ĩ
    0.15
    éĻIJéĩı
    0.12
    ä»»ä½ķæŶåĢĻ
    0.10
    ä»»ä½ķå½¢å¼ı
    0.10
    æѤ类
    0.10
    éĻIJå®ļ
    0.09
    以åħį
    0.09
    éĻIJ度
    0.09
    å¾ĹæĦı
    0.08
    Activations Density 0.081%

    No Known Activations