© 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. 38333
    Prev
    Next
    INDEX
    Explanations

    guide to

    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
    åĸŁ
    -0.09
    æĺİãĤīãģĭ
    -0.08
    人æ°ijæľįåĬ¡
    -0.08
    yle
    -0.08
    èĥŀ
    -0.08
    ahn
    -0.08
    æĢ»æľī
    -0.08
    ä¸Ģ线
    -0.08
    æ¥Ķ
    -0.08
    ä»ĸ人
    -0.08
    POSITIVE LOGITS
    åĤ¬
    0.11
    èĵ¬
    0.09
    失
    0.08
    å¼Ĥåľ°
    0.08
    apult
    0.08
    à¸Īำ
    0.08
    æij§
    0.08
    æł¸å¿ĥæĬĢæľ¯
    0.08
    éĺ²èħIJ
    0.08
    对å¤ĸå¼ĢæĶ¾
    0.08
    Activations Density 0.018%

    No Known Activations