© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50522
    Prev
    Next
    INDEX
    Explanations

    million, billion, grant, Euros

    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
    å¤Ħå¤Ħ
    -0.09
    天æĸĩ
    -0.09
    lob
    -0.09
    æĬĽå¼ĥ
    -0.09
    instanc
    -0.09
     CASCADE
    -0.08
    æĹĭ
    -0.08
    æĤ¬å´ĸ
    -0.08
    æ©IJ
    -0.08
    éģİãģĶ
    -0.08
    POSITIVE LOGITS
    æĬĬè¿Ļ个
    0.10
    设ç«ĭäºĨ
    0.10
    ners
    0.10
    æĬķåħ¥åĪ°
    0.10
    åĪĨæľŁ
    0.09
    ä¸įè¶ħè¿ĩ
    0.09
    å°±æĺ¯ä¸ºäºĨ
    0.08
    æĺ¯ä¸ºäºĨ
    0.08
    åŁ¹
    0.08
    åĪ°ä½į
    0.08
    Activations Density 0.021%

    No Known Activations