© 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. 15880
    Prev
    Next
    INDEX
    Explanations

    technical computing contexts

    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
    å¥ij
    -0.20
    åı¯æĥ³
    -0.19
    鸽
    -0.19
    çļ±çº¹
    -0.19
    æĬĢæľ¯çłĶåıij
    -0.18
    Ñıн
    -0.18
    ä¸īæĸ¹
    -0.18
    SSIP
    -0.18
    ullet
    -0.18
    顺
    -0.18
    POSITIVE LOGITS
     compat
    0.19
     nor
    0.19
     Middleton
    0.18
     pro
    0.18
     or
    0.18
    çļĦæĹ¶ä»£
    0.18
    æijĺ
    0.17
    _safe
    0.17
     spiked
    0.17
    æĪĸèĢħ
    0.17
    Activations Density 0.586%

    No Known Activations