© 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. 1288
    Prev
    Next
    INDEX
    Explanations

    macro prefix for large scale or general context

    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
    TING
    -0.21
    iability
    -0.21
     utmost
    -0.20
    OrCreate
    -0.20
    ermen
    -0.20
     hardcoded
    -0.19
    éĽªèĬ±
    -0.18
     major
    -0.18
     slightest
    -0.18
    ä¸Ĭæĸ¹
    -0.18
    POSITIVE LOGITS
    scopic
    0.38
    ship
    0.29
    们
    0.25
    ä¸ĢçĤ¹åĦ¿
    0.23
    itect
    0.21
    åĩºåĩ»
    0.21
    们éĥ½
    0.20
    à¸ģาย
    0.19
    lor
    0.19
    åĮĸçļĦ
    0.19
    Activations Density 0.018%

    No Known Activations