© 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. 11579
    Prev
    Next
    INDEX
    Explanations

    playing around with something

    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
    LAG
    -0.23
    åĨĢ
    -0.19
    çĽ¸ä¿¡
    -0.19
    bis
    -0.19
     sẵn
    -0.19
    ç´§å¯Ĩ
    -0.19
    åįĹæ²Ļ
    -0.18
    æŃ£æĺ¯åĽłä¸º
    -0.18
    è¡©
    -0.18
     пÑĢавиÑĤелÑĮ
    -0.18
    POSITIVE LOGITS
    好çİ©
    0.37
    çİ©èĢį
    0.37
    çİ©æ³ķ
    0.34
    çİ©
    0.31
    æĪı
    0.28
    çİ©åħ·
    0.28
    å®ŀéªĮ
    0.27
    åħ´è¶£
    0.26
    æľī趣çļĦ
    0.26
     toy
    0.26
    Activations Density 0.161%

    No Known Activations