© 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. 12700
    Prev
    Next
    INDEX
    Explanations

    dates and durations

    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
    aic
    -0.22
    Bus
    -0.20
    对çŃĸ
    -0.19
     Distrib
    -0.19
    licit
    -0.19
     Budd
    -0.19
    åĨ¢
    -0.19
     Milk
    -0.19
    ôn
    -0.19
    tract
    -0.19
    POSITIVE LOGITS
    æĹºåŃ£
    0.26
     bookings
    0.23
    æĢ»ä»·
    0.22
    欧å¼ı
    0.22
    åŃ£èĬĤ
    0.21
    é¢Ħ订
    0.20
    romise
    0.20
    UCH
    0.20
    çĮ¿
    0.20
     booked
    0.20
    Activations Density 0.039%

    No Known Activations