© 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. 3118
    Prev
    Next
    INDEX
    Explanations

    processing automatically

    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
    semb
    -0.27
    ç»ĵæĻ¶
    -0.24
    æĹ¶è¡¨ç¤º
    -0.23
    临
    -0.23
    å®Įå·¥
    -0.23
     Passage
    -0.23
    .createObject
    -0.22
    ãģ°ãģĭãĤĬ
    -0.22
    çļĦ表çİ°
    -0.22
    pst
    -0.22
    POSITIVE LOGITS
    åıĹçIJĨ
    0.38
    å®¡æł¸
    0.37
    æ±ĩæĢ»
    0.33
    æł¸å®ŀ
    0.32
    æĶ¶åĪ°
    0.31
     processing
    0.30
    æİ¥æĶ¶
    0.30
     automatically
    0.29
    æİ¥åıĹ
    0.29
    æĶ¶éĽĨ
    0.29
    Activations Density 0.121%

    No Known Activations