© 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. 392
    Prev
    Next
    INDEX
    Explanations

    Energy, Filter, Resort, PIO, Shoot

    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
    consult
    -0.24
    æĨİ
    -0.23
    èĶ«
    -0.23
    楹
    -0.22
    åīįæıIJæĺ¯
    -0.22
     Tire
    -0.22
    ANTE
    -0.22
     MATERIAL
    -0.21
     Expense
    -0.21
    èĵij
    -0.21
    POSITIVE LOGITS
    举åĮĹ
    0.24
    koa
    0.23
     gag
    0.23
     statt
    0.23
    Anywhere
    0.22
    prs
    0.22
    ä¼ĺè´¨
    0.22
    éĿĻ
    0.22
    rack
    0.21
     quietly
    0.21
    Activations Density 0.277%

    No Known Activations