© 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. 198
    Prev
    Next
    INDEX
    Explanations

    time indicator after "at"

    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
    æī§
    -0.26
     lẽ
    -0.24
    åĽ«
    -0.23
    åħijæį¢
    -0.22
    çªĺ
    -0.22
    éĻ¢éĻ¢éķ¿
    -0.21
    Loads
    -0.21
    :UI
    -0.21
    ohana
    -0.21
    AIR
    -0.20
    POSITIVE LOGITS
    ä¸ĢèĪ¬
    0.29
     Cum
    0.26
    adj
    0.26
    fly
    0.24
    æľĢè¿ij
    0.24
    latest
    0.24
    累计
    0.23
    adora
    0.22
    cup
    0.22
    uum
    0.22
    Activations Density 0.017%

    No Known Activations