© 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. 1672
    Prev
    Next
    INDEX
    Explanations

    introduces future actions or capabilities

    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
    为æĤ¨
    -0.12
    被迫
    -0.10
    æĪijä¸Ģ缴
    -0.10
    å§ĭç»Ī
    -0.10
    ichel
    -0.09
    æĤ¨åı¯ä»¥
    -0.09
    欣
    -0.09
    é»į
    -0.09
    çĹĽ
    -0.09
    å¦ĤæľŁ
    -0.09
    POSITIVE LOGITS
    æį®è¯´
    0.13
    让çĶ¨æĪ·
    0.12
    æį®æĤī
    0.12
    å°Ĩæĺ¯
    0.11
    æį®ä»ĭç»į
    0.11
    é¦ĸæī¹
    0.10
    ãģ¨ãģ®ãģĵãģ¨
    0.10
    æį®äºĨ解
    0.09
    æį®
    0.09
     reportedly
    0.09
    Activations Density 0.179%

    No Known Activations