© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1891
    Prev
    Next
    INDEX
    Explanations

    exercise and fitness

    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
    æľªæĪIJ
    -0.26
    æī§æĦı
    -0.26
    fallback
    -0.26
    åħ¬å¼Ģ
    -0.25
    å¤±æľĽ
    -0.25
    alien
    -0.25
    åĩºåı°
    -0.24
    çijķçĸµ
    -0.24
    åıĤèĢĥ
    -0.24
    æī¿è¯º
    -0.24
    POSITIVE LOGITS
     aerobic
    0.41
    éĶ»çĤ¼
    0.37
    æ¶ĪèĢĹ
    0.33
     workout
    0.32
    åĩºæ±Ĺ
    0.31
     calorie
    0.31
    -body
    0.31
     cardiovascular
    0.30
    身ä½ĵ
    0.30
    /body
    0.30
    Activations Density 0.028%

    No Known Activations