© 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. 14147
    Prev
    Next
    INDEX
    Explanations

    diagnoses and treatments

    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
    çĸµ
    -0.25
    æı¡
    -0.24
     поÑģколÑĮ
    -0.23
     pornost
    -0.23
     prostituer
    -0.23
     erotisk
    -0.23
     knull
    -0.23
     salopes
    -0.23
     rumpe
    -0.22
    ãĮ¢
    -0.22
    POSITIVE LOGITS
     Luo
    0.22
    æݨèįIJ
    0.21
     recommended
    0.21
     metabolic
    0.21
     suspected
    0.20
     metab
    0.20
     biom
    0.20
     recommend
    0.20
    èĢģ人家
    0.19
    éĻ§
    0.19
    Activations Density 0.060%

    No Known Activations