© 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. 1102
    Prev
    Next
    INDEX
    Explanations

    would lead 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
    ︰
    -0.09
    æī¾åĪ°äºĨ
    -0.09
    æĺİçĻ½äºĨ
    -0.09
    幡
    -0.09
    ç»Īäºİ
    -0.09
    è§ħ
    -0.08
    åĶ¬
    -0.08
    æıIJä¾ĽäºĨ
    -0.08
    欣æħ°
    -0.08
    ä»ŀ
    -0.08
    POSITIVE LOGITS
    ä¸ĩä¸Ģ
    0.13
    太
    0.11
    ä¸įåĪ©äºİ
    0.10
    would
    0.10
     Would
    0.10
    太å¤ļ
    0.10
     too
    0.10
    Would
    0.09
    Too
    0.09
     would
    0.09
    Activations Density 0.277%

    No Known Activations