© 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. 1525
    Prev
    Next
    INDEX
    Explanations

    identity descriptors and associated roles

    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
    失败
    -0.32
    æĦļèł¢
    -0.30
     stupid
    -0.30
     ridiculous
    -0.29
     failures
    -0.29
     silly
    -0.29
    èł¢
    -0.28
    笨
    -0.28
    failure
    -0.28
     madness
    -0.27
    POSITIVE LOGITS
     اÙĦÙĥرÙĬÙħ
    0.23
     fluid
    0.23
    Pow
    0.23
    麻å°Ĩ
    0.22
    çİ°è´§
    0.22
    ophone
    0.22
    æĹłæĦı
    0.22
    ulet
    0.22
    åıĮåIJij
    0.22
    åħ¬å¼ĢèµĽ
    0.21
    Activations Density 0.267%

    No Known Activations