© 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. 14264
    Prev
    Next
    INDEX
    Explanations

    winning advantage and superiority

    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
    lein
    -0.21
    åIJ¯çĶ¨
    -0.21
    stre
    -0.19
    onders
    -0.19
    骨
    -0.19
    顺åºĶ
    -0.19
    åīįæīĢ
    -0.18
    hf
    -0.18
    utor
    -0.18
    æī©
    -0.18
    POSITIVE LOGITS
     tail
    0.23
    æ·Ģ
    0.21
    å°¾
    0.21
    -over
    0.20
     Tail
    0.20
    .documentation
    0.20
    .tail
    0.20
    Tail
    0.19
    .sap
    0.19
    嵯
    0.19
    Activations Density 0.036%

    No Known Activations