© 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. 13531
    Prev
    Next
    INDEX
    Explanations

    questions about technical concepts

    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¤įæŁ¥
    -0.20
    red
    -0.17
    å¼Ģåĩº
    -0.17
    èĥ½åĬĽåĴĮ
    -0.16
    åħŃåIJĪ
    -0.16
    olk
    -0.16
    æĮĩ令
    -0.16
    deck
    -0.16
     cach
    -0.16
    aza
    -0.16
    POSITIVE LOGITS
     ÑģобÑģÑĤвенно
    0.22
    è¿ĺåĮħæĭ¬
    0.21
    尤为
    0.21
    (Font
    0.19
    å°¤
    0.19
     кÑĢед
    0.18
    ä¸įåĪĨ
    0.18
    æģIJæĢķ
    0.17
    æľIJ
    0.17
    orris
    0.17
    Activations Density 0.303%

    No Known Activations