© 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. 1217
    Prev
    Next
    INDEX
    Explanations

    national scope and reach

    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
    âij
    -0.28
    æľĶ
    -0.26
    ar
    -0.25
    éĢı
    -0.24
    åĥļ
    -0.24
    Decl
    -0.23
    å¼
    -0.23
    reff
    -0.22
    æĺŃ
    -0.22
     hos
    -0.22
    POSITIVE LOGITS
     Relatives
    0.26
     Smoke
    0.24
    breadcrumb
    0.23
    èĮĥåĽ´åĨħ
    0.23
    .asList
    0.23
     DPI
    0.23
    xEB
    0.22
    æĪ´çĿĢ
    0.22
    jac
    0.22
    çŁ¥åIJįçļĦ
    0.22
    Activations Density 0.052%

    No Known Activations