© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1066
    Prev
    Next
    INDEX
    Explanations

    orchestra and symphony performances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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¸ĤæķĻèĤ²
    -0.23
    =len
    -0.23
    æijĺè¦ģ
    -0.23
    æĮĩå¼ķ
    -0.22
    (math
    -0.22
    ä¸ŃåĽ½æĶ¿åºľ
    -0.22
    å¤Ħ
    -0.21
    chr
    -0.21
    Boxes
    -0.21
    åłł
    -0.21
    POSITIVE LOGITS
    ä¹IJåĽ¢
    0.31
     Orchestra
    0.29
    éĺµå®¹
    0.28
     touring
    0.28
    æĪIJåijĺ
    0.27
    åľĺ
    0.26
     orchestra
    0.25
     commuting
    0.25
    åĽ¢
    0.24
     voted
    0.24
    Activations Density 0.020%

    No Known Activations