© 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. 36472
    Prev
    Next
    INDEX
    Explanations

    visible occurrences

    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·¢
    -0.09
    åĬ¨çī©åĽŃ
    -0.09
    丼
    -0.09
    ç¼ī
    -0.08
    ä»İæł¹æľ¬ä¸Ĭ
    -0.08
    ä¸įåĨįæĺ¯
    -0.08
    æĪIJçĨŁçļĦ
    -0.08
    éķ¿çŁŃ
    -0.08
    峦
    -0.08
    2
    -0.07
    POSITIVE LOGITS
    åIJį人
    0.11
    çݰ身
    0.10
    大éĥ¨åĪĨ人
    0.10
    éľ²åĩº
    0.10
    çŁ¥åIJį度
    0.10
     visible
    0.10
    æĽ´å®¹æĺĵ
    0.10
    ä¸į便
    0.10
    visibility
    0.09
    Visible
    0.09
    Activations Density 0.133%

    No Known Activations