© 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. 9677
    Prev
    Next
    INDEX
    Explanations

    marked icons

    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
    çĶ¨æĪ·æıIJä¾Ľ
    -0.10
    ä¸įäºĨ
    -0.09
     Ernest
    -0.09
    pei
    -0.08
    ún
    -0.08
    ../../../../
    -0.08
    佬
    -0.08
    eded
    -0.08
    ../../../
    -0.08
    ｨ
    -0.08
    POSITIVE LOGITS
    ï¸ı
    0.20
    æĦıä¹īä¸Ĭ
    0.10
    ably
    0.10
    åĮºå§Ķ
    0.09
    ãģĹãģ¾ãģĨ
    0.09
    ê¹IJ
    0.09
    ayers
    0.09
    ingly
    0.09
    ABILITY
    0.09
    ×ķ
    0.08
    Activations Density 0.007%

    No Known Activations