© 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. 14005
    Prev
    Next
    INDEX
    Explanations

    company and ownership contexts

    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
    åĥ°
    -0.21
    å¦Ī
    -0.21
    æĹłæīĢ
    -0.20
    说å®ŀ
    -0.19
     HERO
    -0.18
    å½¢
    -0.18
    çıĪ
    -0.18
     ка
    -0.18
    ç»Ļä»ĸ们
    -0.18
    éĤ¦
    -0.18
    POSITIVE LOGITS
    å§Ķæīĺ
    0.22
    å¤ļæĸ¹
    0.21
    产éĩı
    0.21
    å®ŀéĻħæݧåĪ¶
    0.21
    æĮģæľīçļĦ
    0.20
    æīĢæľīæĿĥ
    0.20
    秣èµģ
    0.20
    代çIJĨ人
    0.20
     Holden
    0.19
    æĪĺçķ¥åIJĪä½ľ
    0.19
    Activations Density 0.015%

    No Known Activations