© 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. 2212
    Prev
    Next
    INDEX
    Explanations

    too much

    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
    åīįæĻ¯
    -0.24
     currently
    -0.24
     freely
    -0.23
    åİŁæłĩé¢ĺ
    -0.23
    ä¸Ĭç½ij
    -0.23
    uture
    -0.22
    oot
    -0.22
    mes
    -0.22
    .#
    -0.22
     Profile
    -0.21
    POSITIVE LOGITS
    äºİæĺ¯
    0.32
    æĸ¼æĺ¯
    0.27
    Suddenly
    0.27
     resulting
    0.25
    æĦıæĥ³ä¸įåĪ°
    0.25
     Upon
    0.24
    zas
    0.24
     Quickly
    0.24
     forgot
    0.24
     Consequently
    0.23
    Activations Density 0.134%

    No Known Activations