© 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. 11520
    Prev
    Next
    INDEX
    Explanations

    pass, ticket, fare

    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
    æ¯ıåij¨
    -0.20
    (deg
    -0.19
     Nev
    -0.19
    usercontent
    -0.19
    tractor
    -0.18
    éħ¾
    -0.18
    ctal
    -0.18
    orce
    -0.18
    ÃŃcia
    -0.18
    ktor
    -0.18
    POSITIVE LOGITS
    çģµæ´»
    0.23
    å°±è¿ij
    0.22
    åľ¨ç½ijä¸Ĭ
    0.22
    临æŶ
    0.21
    å¾Ģè¿Ķ
    0.20
    纸质
    0.20
    票
    0.20
    åºĶä»ĺ
    0.20
     tickets
    0.19
    å¢ĥåĨħ
    0.19
    Activations Density 0.010%

    No Known Activations