© 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. 14744
    Prev
    Next
    INDEX
    Explanations

    three/triple prefixes

    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
    urma
    -0.23
    两家
    -0.23
    èѬ
    -0.21
    çIJĨåıij
    -0.20
    è¾ĥ强çļĦ
    -0.20
    å¤ļ家
    -0.19
    æ²IJæµ´
    -0.19
    举æĸ¹
    -0.19
    (px
    -0.19
    ç¬ĭ
    -0.18
    POSITIVE LOGITS
    å¸ģ
    0.22
    resses
    0.20
    å¹£
    0.20
    instead
    0.20
     chứ
    0.19
    itness
    0.19
    utt
    0.19
     instead
    0.19
    rag
    0.19
     bust
    0.18
    Activations Density 0.128%

    No Known Activations