© 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. 17273
    Prev
    Next
    INDEX
    Explanations

    periodic cycles and periods

    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
    Negative Logits
     Sok
    -0.21
    acam
    -0.19
    zers
    -0.19
    çĤ¹äºĨ
    -0.19
    .activ
    -0.19
    室
    -0.18
    åĻª
    -0.18
    èµ·é£ŀ
    -0.18
    drops
    -0.18
    habi
    -0.18
    POSITIVE LOGITS
    åij¨æľŁ
    0.62
     cycle
    0.52
    循çݯ
    0.46
     cycles
    0.45
    _cycle
    0.43
    cycle
    0.42
    Cycle
    0.42
     Cycle
    0.40
    è½®åĽŀ
    0.40
    .cycle
    0.39
    Activations Density 0.084%

    No Known Activations