© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52261
    Prev
    Next
    INDEX
    Explanations

    sorry for mistake or missed opportunity

    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
    éĩįè¦ģåĽłç´ł
    -0.11
    ><![
    -0.10
    èĶ«
    -0.09
    çļĦåį°è±¡
    -0.09
    è¶Ĭé«ĺ
    -0.09
    å°±åı¯ä»¥äºĨ
    -0.09
    å°±è¡ĮäºĨ
    -0.09
    ÑĥÑĩа
    -0.09
    åĹ¡
    -0.09
    æĤ¬å¿µ
    -0.09
    POSITIVE LOGITS
    sorry
    0.09
    Sorry
    0.08
    esi
    0.08
    碰
    0.08
    æļĤ
    0.08
    ansk
    0.08
    rij
    0.08
    æļ«
    0.08
     Currently
    0.08
    brid
    0.08
    Activations Density 0.018%

    No Known Activations