© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16951
    Prev
    Next
    INDEX
    Explanations

    spatio-temporal

    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
    åĬ©éķ¿
    -0.20
    ä¸İåIJ¦
    -0.20
    oire
    -0.20
    rab
    -0.19
    èį¦
    -0.19
    å°ıå¿ĥ
    -0.18
    å¸ľ
    -0.18
    .tbl
    -0.18
    LF
    -0.18
    çĪ±å°Ķ
    -0.18
    POSITIVE LOGITS
    æŶéĹ´
    0.31
     time
    0.30
    跨度
    0.29
    (time
    0.28
     interval
    0.28
    æĻĤéĸĵ
    0.28
     اÙĦزÙħÙĨ
    0.27
    /time
    0.27
     æŶéĹ´
    0.26
    æµģéĢĿ
    0.25
    Activations Density 0.107%

    No Known Activations