© 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. 257
    Prev
    Next
    INDEX
    Explanations

    electroencephalogram or EEG

    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
    overs
    -0.24
    éĢĨ转
    -0.23
    acers
    -0.23
     tiên
    -0.22
    Spin
    -0.22
     kicked
    -0.22
     Candidates
    -0.22
    adius
    -0.22
    磫
    -0.21
    units
    -0.21
    POSITIVE LOGITS
     Mour
    0.24
     clutter
    0.22
     hassle
    0.22
     renew
    0.22
    agal
    0.21
    头çļ®
    0.21
    moz
    0.21
    SourceType
    0.21
     EEG
    0.21
    馥
    0.21
    Activations Density 0.050%

    No Known Activations