© 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. 12707
    Prev
    Next
    INDEX
    Explanations

    e-commerce platforms and code

    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
    é©»
    -0.21
    Verb
    -0.18
    é§IJ
    -0.18
    arn
    -0.18
     prophecy
    -0.18
     stochastic
    -0.18
    abra
    -0.18
     resid
    -0.18
    ä½ĵéĩı
    -0.18
    éļ¶
    -0.17
    POSITIVE LOGITS
     merchandise
    0.26
    alers
    0.22
     merch
    0.20
    åIJĪéĩij
    0.20
    æĨ¬
    0.20
    _CFG
    0.19
     ATK
    0.19
    WARE
    0.18
    æĬĺæī£
    0.18
    大å®Ĺ
    0.18
    Activations Density 0.096%

    No Known Activations