© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14485
    Prev
    Next
    INDEX
    Explanations

    sedative effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    maf
    -0.20
    çľīæ¯Ľ
    -0.20
    orns
    -0.19
    .cycle
    -0.19
     Marco
    -0.19
    chg
    -0.18
    æĶ»
    -0.18
    çĸ½
    -0.18
    [min
    -0.18
    ror
    -0.17
    POSITIVE LOGITS
    åħ¥çĿ¡
    0.29
    çĿ¡
    0.27
     sleep
    0.27
    çĿ¡çľł
    0.27
    çĿ¡åīį
    0.25
    Sleep
    0.25
    sleep
    0.24
    åīĤ
    0.24
     sleeping
    0.23
    åĬij
    0.23
    Activations Density 0.087%

    No Known Activations