© 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
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 525
    Prev
    Next
    INDEX
    Explanations

    same or duplicate

    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
    sand
    -0.27
    gend
    -0.24
    odia
    -0.24
    çļĦ女åĦ¿
    -0.24
    lected
    -0.23
    æŀ¢
    -0.23
    çļĦæĹ¥åŃIJ
    -0.23
    奢
    -0.23
     hybrid
    -0.22
     pinch
    -0.22
    POSITIVE LOGITS
     Bulk
    0.24
    éĥ¨åĪĨåĨħ容
    0.24
    browser
    0.22
     MISS
    0.22
    åĪ¶
    0.21
     LPC
    0.21
    UTO
    0.21
    éĿ¢çĽ®
    0.21
    åį°è±¡
    0.21
    ffen
    0.21
    Activations Density 0.019%

    No Known Activations