© 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. 10909
    Prev
    Next
    INDEX
    Explanations

    what to do

    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
    sters
    -0.19
    è¦ģçŁ¥éģĵ
    -0.18
    ä¹Łæĺ¯ä¸Ģ个
    -0.18
    ä¹Łæĺ¯éĿŀ常
    -0.18
     propri
    -0.18
    VERY
    -0.18
    è¿Ļä¹Łæĺ¯
    -0.18
     Ñģобой
    -0.17
    æīĢè¬Ĥ
    -0.17
    GEST
    -0.17
    POSITIVE LOGITS
    éĢīæĭ©
    0.25
    /how
    0.21
    åIJĥçļĦ
    0.20
    åģļçļĦ
    0.19
    åĪĨéħį
    0.19
    orman
    0.18
    éĩĩ
    0.18
    åħ³æ³¨
    0.18
    åģļçļĦäºĭ
    0.18
    磾
    0.18
    Activations Density 0.054%

    No Known Activations