© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 26
    Prev
    Next
    INDEX
    Explanations

    book titles and guides

    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
    æīĵæĸŃ
    -0.26
     Submitted
    -0.24
    _hop
    -0.23
     indirectly
    -0.23
    æĮĤåı·
    -0.23
    é£
    -0.23
    ä¾Ľç»Ļ侧
    -0.23
     заÑıв
    -0.22
    Registrar
    -0.22
    æ»´æ»´
    -0.22
    POSITIVE LOGITS
     series
    0.35
    ãĤ·ãĥªãĥ¼ãĤº
    0.33
    series
    0.32
    ç³»åĪĹ
    0.31
     Paperback
    0.29
     ÑģеÑĢии
    0.29
    ä¸Ľä¹¦
    0.28
     Infer
    0.28
    åħ¥éŨ
    0.27
     encyclopedia
    0.27
    Activations Density 0.055%

    No Known Activations