© 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. 2146
    Prev
    Next
    INDEX
    Explanations

    after a specific event or time

    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
     really
    -0.26
     sometimes
    -0.26
     mix
    -0.25
     maybe
    -0.24
     better
    -0.24
     generally
    -0.24
     definitely
    -0.24
     l
    -0.23
     things
    -0.23
     weak
    -0.23
    POSITIVE LOGITS
    æѤåīį
    0.35
    ç´§æİ¥çĿĢ
    0.30
     Earlier
    0.29
     afterward
    0.29
    åľ¨æѤä¹ĭåīį
    0.28
     earlier
    0.28
    è¿Ļåľº
    0.28
    è¿ĻæĿ¡
    0.27
     dabei
    0.27
    anka
    0.27
    Activations Density 0.385%

    No Known Activations