© 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. 56841
    Prev
    Next
    INDEX
    Explanations

    a big fan

    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
    æĹłäºº
    -0.10
    黾
    -0.10
    ä¸ĭ次
    -0.10
    èľķ
    -0.09
    åİ¢
    -0.08
    åģļåĪ°äºĨ
    -0.08
    ç§Ģ
    -0.08
    ãĤĭãģ®ãģ¯
    -0.08
    误解
    -0.08
    仿
    -0.08
    POSITIVE LOGITS
    éĩįè§Ĩ
    0.10
    é»į
    0.10
    èĭĽ
    0.10
    çĿļ
    0.09
    çľĭéĩį
    0.09
    çİ»çĴĥ
    0.09
    èī²å½©
    0.09
    ä»İå°ı
    0.09
    åīįèĢħ
    0.09
    å½±éŁ³
    0.09
    Activations Density 0.046%

    No Known Activations