© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3249
    Prev
    Next
    INDEX
    Explanations

    et al

    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
    Negative Logits
    ä¸ĭä¸Ģ个
    -0.24
    -next
    -0.24
    責
    -0.23
    ÙĬÙĦا
    -0.23
     Plenty
    -0.22
     getNext
    -0.22
    Coach
    -0.21
    next
    -0.21
    Pictures
    -0.21
    éĺŁéķ¿
    -0.21
    POSITIVE LOGITS
     et
    0.49
    çŃī人
    0.39
    .et
    0.31
    åĨĻéģĵ
    0.26
    使çĶ¨ç¶²è·¯
    0.25
    èĥ½åĬĽåĴĮ
    0.25
    etal
    0.25
    æ°ı
    0.25
     argues
    0.24
     eta
    0.23
    Activations Density 0.188%

    No Known Activations