© 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. 1001
    Prev
    Next
    INDEX
    Explanations

    exercise and medical tests

    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
    饴
    -0.25
     heg
    -0.23
    èĽĭ
    -0.23
     bast
    -0.23
    åıĸ代
    -0.22
     adamant
    -0.22
     Pulitzer
    -0.22
     destin
    -0.21
     mess
    -0.21
     deleg
    -0.21
    POSITIVE LOGITS
    æµĭè¯ķ
    0.46
     tests
    0.41
     testing
    0.39
    testing
    0.39
    ĭè¯ķ
    0.36
     test
    0.36
    ptest
    0.36
    ãĥĨãĤ¹ãĥĪ
    0.36
     stimulated
    0.35
    Testing
    0.35
    Activations Density 0.947%

    No Known Activations