© 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. 143
    Prev
    Next
    INDEX
    Explanations

    e-readers, reading devices

    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
    æİĴ污
    -0.26
     mpi
    -0.24
    _mpi
    -0.24
    éķĹ
    -0.24
    æĪIJ份
    -0.23
    guarded
    -0.23
     concurrently
    -0.23
     obed
    -0.23
    æ°°
    -0.23
    éĴ¢ç®¡
    -0.23
    POSITIVE LOGITS
    éĺħ读
    0.41
     Kindle
    0.40
    书åºĹ
    0.39
     reading
    0.39
     Reading
    0.39
     readability
    0.38
     tablet
    0.38
    Reading
    0.37
    çľĭ书
    0.36
     iPad
    0.35
    Activations Density 0.031%

    No Known Activations