© 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. 15413
    Prev
    Next
    INDEX
    Explanations

    organic or const variables

    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
    ilar
    -0.20
    waÄĩ
    -0.20
    rome
    -0.20
    rega
    -0.20
    venir
    -0.20
    -Bar
    -0.19
    è¹Ĵ
    -0.19
    ollo
    -0.18
    essim
    -0.18
    .dds
    -0.18
    POSITIVE LOGITS
    级åĪ«çļĦ
    0.22
    æĹ¥åĩĮæĻ¨
    0.21
    约åįł
    0.21
    åĽĽåŃ£
    0.20
    çĨŁ
    0.19
     quantities
    0.18
    lte
    0.18
    èµłéĢģ
    0.18
    éĩįä¸Ńä¹ĭéĩį
    0.18
    äºĮåįģäºĶ
    0.18
    Activations Density 0.016%

    No Known Activations