© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15135
    Prev
    Next
    INDEX
    Explanations

    end of

    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
    ç¢į
    -0.21
    å¿Ŀ
    -0.18
    涯
    -0.18
     elsewhere
    -0.17
    lessly
    -0.17
     matters
    -0.17
    resse
    -0.17
    åľ¨åĨħçļĦ
    -0.17
    tee
    -0.17
    åīį身
    -0.17
    POSITIVE LOGITS
    warts
    0.21
    ä¸Ģ段æŶéĹ´
    0.21
    æĹ¶æľŁ
    0.19
    âĺł
    0.18
    éĺħ读åħ¨æĸĩ
    0.17
    产ä¸ļéĵ¾
    0.17
    /on
    0.17
     Maurice
    0.17
    oucher
    0.17
    /top
    0.17
    Activations Density 0.020%

    No Known Activations