© 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. 148
    Prev
    Next
    INDEX
    Explanations

    day of the week

    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
     ongoing
    -0.22
    rd
    -0.21
    ries
    -0.20
    edom
    -0.20
    ä¸įéĶĻ
    -0.19
    awy
    -0.18
    osta
    -0.18
    еннÑĥÑİ
    -0.18
    ockey
    -0.17
    ream
    -0.17
    POSITIVE LOGITS
    itored
    0.21
    çĥŃæIJľ
    0.21
     mornings
    0.21
    ../../../
    0.20
    eel
    0.20
    çĵ¢
    0.20
     morning
    0.20
    st
    0.20
    gers
    0.20
    -ish
    0.20
    Activations Density 0.025%

    No Known Activations