© 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. 567
    Prev
    Next
    INDEX
    Explanations

    musical instruments and performers

    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
    objs
    -0.27
    uffy
    -0.26
    bucks
    -0.25
    çļĦæĪ¿åŃIJ
    -0.24
    èĮ¬
    -0.23
    åģ¾
    -0.23
     ships
    -0.23
     objs
    -0.22
    ç¥ł
    -0.22
     outnumber
    -0.22
    POSITIVE LOGITS
    çĭ¬
    0.28
    å²ģæľĪ
    0.25
    çĭ¬èĩª
    0.25
     Carn
    0.24
     His
    0.24
    -lnd
    0.24
     commissions
    0.24
    His
    0.24
     solo
    0.24
     Ger
    0.23
    Activations Density 0.013%

    No Known Activations