© 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. 12799
    Prev
    Next
    INDEX
    Explanations

    Japanese Chinese words

    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
     Vacation
    -0.20
    Maybe
    -0.20
    Ny
    -0.19
     Alpine
    -0.19
    ania
    -0.18
    éĤ£è¾¹
    -0.18
    çĸı
    -0.18
     maybe
    -0.18
    .fromString
    -0.17
    è©
    -0.17
    POSITIVE LOGITS
    ä»»ä½ķæŶåĢĻ
    0.24
    åĤ¨åŃĺ
    0.23
    ä¹Łåı¯
    0.23
    延伸
    0.21
    åıijå±ķæĸ¹åIJij
    0.21
    羣æŃ£åģļåĪ°
    0.21
    èµĥ
    0.20
    éķ¿è¾¾
    0.20
    sti
    0.19
    ä¹Łåı¯ä»¥
    0.19
    Activations Density 0.007%

    No Known Activations