© 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. 12969
    Prev
    Next
    INDEX
    Explanations

    carbon freezing

    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
    åij½é¢ĺ
    -0.21
    éĻªä¼´
    -0.19
    æĻ®
    -0.19
    åľ¨çĶŁæ´»ä¸Ń
    -0.19
    bens
    -0.19
    urable
    -0.18
    线索
    -0.18
    loor
    -0.18
     Ped
    -0.18
    åı£æ°Ķ
    -0.18
    POSITIVE LOGITS
    åIJĦæĸ¹
    0.20
    ä¾Ŀ次
    0.19
    igan
    0.18
    _MACHINE
    0.18
    åIJĥäºı
    0.18
    æ¼ı
    0.18
     обоÑĢ
    0.18
    _PAD
    0.17
    è¦Ĩ
    0.17
    ecs
    0.17
    Activations Density 0.004%

    No Known Activations