© 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
    2. Qwen3-8B
    3. 18-RESID-BATCHTOPK-65K__L0-80
    4. 1339
    Prev
    Next
    INDEX
    Explanations

    teach skills for life

    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
    çĸ²
    -0.24
     official
    -0.23
    年度
    -0.23
     Petro
    -0.22
    被æįķ
    -0.22
    ilon
    -0.22
    _Internal
    -0.22
     accommod
    -0.22
    浪潮
    -0.21
    æĪ´çĿĢ
    -0.21
    POSITIVE LOGITS
     lifelong
    0.38
    æĩĤå¾Ĺ
    0.36
    åѦä¼ļ
    0.36
    è¦ģåѦä¼ļ
    0.36
    人çĶŁçļĦ
    0.35
    çļĦ人çĶŁ
    0.34
    åģļ人
    0.32
    人çĶŁ
    0.32
    çݰå®ŀçĶŁæ´»
    0.31
     skills
    0.31
    Activations Density 0.064%

    No Known Activations