© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1945
    Prev
    Next
    INDEX
    Explanations

    Is followed by specific entities

    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
    å¼łè´´
    -0.25
    梢
    -0.23
    ìĩł
    -0.22
    æ½¢
    -0.21
     PROGMEM
    -0.21
     resourceId
    -0.21
    éķĩæĶ¿åºľ
    -0.21
     DefaultValue
    -0.21
    dojo
    -0.21
    åĪ©çī©
    -0.20
    POSITIVE LOGITS
     famously
    0.33
     himself
    0.28
    -esque
    0.28
    contr
    0.25
    æĪĸåħ¶ä»ĸ
    0.24
    uman
    0.24
    æĸ°ä¸Ģ代
    0.24
    ç¾İåĽ½æĢ»ç»Ł
    0.24
    NYSE
    0.23
     blockbuster
    0.23
    Activations Density 0.191%

    No Known Activations