© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2301
    Prev
    Next
    INDEX
    Explanations

    annual awards and prizes

    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
     speed
    -0.26
     strip
    -0.25
    Everything
    -0.25
     escape
    -0.24
    keit
    -0.24
     siêu
    -0.24
     navigator
    -0.23
    ikal
    -0.23
    upy
    -0.23
    avig
    -0.23
    POSITIVE LOGITS
    æ¯ıå¹´
    0.56
    å¥ĸ项
    0.52
     annually
    0.47
    åIJįé¢Ŀ
    0.47
    å¥ĸåĬ±
    0.45
     annual
    0.42
    æ¯ıå¹´éĥ½
    0.41
     awards
    0.41
    é¢ģåıij
    0.41
     prizes
    0.40
    Activations Density 0.083%

    No Known Activations