© 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. 1020
    Prev
    Next
    INDEX
    Explanations

    sections and folders

    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
    rosse
    -0.25
    .perform
    -0.25
     diam
    -0.23
    çıł
    -0.23
    amed
    -0.23
    kers
    -0.22
    ROSS
    -0.22
    ANGO
    -0.22
    _initializer
    -0.22
    RYPT
    -0.22
    POSITIVE LOGITS
    æłı
    0.38
     section
    0.37
    æĿ¿åĿĹ
    0.33
     Miscellaneous
    0.31
    section
    0.31
     folders
    0.30
    èıľåįķ
    0.30
     listings
    0.30
     category
    0.30
     folder
    0.30
    Activations Density 0.222%

    No Known Activations