© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 268
    Prev
    Next
    INDEX
    Explanations

    attention deficit hyperactivity disorder

    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
    cloth
    -0.23
    ULA
    -0.23
    HEADER
    -0.22
    лог
    -0.22
    UT
    -0.21
    aura
    -0.21
    ULE
    -0.21
    _ng
    -0.21
    alive
    -0.21
    ä¸Ģ个æĸ°çļĦ
    -0.21
    POSITIVE LOGITS
    ç°Ł
    0.24
     arc
    0.23
    æĤ±
    0.22
     anc
    0.21
     NOTICE
    0.21
     Gent
    0.21
    eden
    0.21
    åĮĹæĸĹ
    0.20
     atomic
    0.20
    erring
    0.20
    Activations Density 0.003%

    No Known Activations