© 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. 2381
    Prev
    Next
    INDEX
    Explanations

    daily life routines

    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
    atre
    -0.26
     оÑĤказ
    -0.24
     achievement
    -0.24
    éĢłä»·
    -0.23
    orate
    -0.23
    acent
    -0.22
    éī´åĪ«
    -0.22
     apt
    -0.22
    UTURE
    -0.22
    atel
    -0.22
    POSITIVE LOGITS
    æŃ£å¸¸çļĦ
    0.35
     routines
    0.34
    usual
    0.32
     usual
    0.30
     whatever
    0.30
    routine
    0.29
    åIJĦèĩª
    0.29
     routine
    0.28
    (normal
    0.28
     normal
    0.28
    Activations Density 0.020%

    No Known Activations