© 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. 11276
    Prev
    Next
    INDEX
    Explanations

    Ayn Rand, Liferay, Phabricator, Gibran

    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
    åĬŁå¾·
    -0.22
    ä¸įåĩºæĿ¥
    -0.21
    æ·±æ·±åľ°
    -0.20
    å·¥ç¨ĭæĬĢæľ¯
    -0.19
    ä¸īæĿ¡
    -0.19
    æ·Ħ
    -0.19
    èµ·æĿ¥äºĨ
    -0.18
    ä¹Łæ²¡ä»Ģä¹Ī
    -0.18
    åĿļ飧
    -0.18
    ãĤ·ãĥ³
    -0.18
    POSITIVE LOGITS
     наÑģÑĤоÑıÑī
    0.20
    uhan
    0.19
    vision
    0.19
    lij
    0.19
     HUD
    0.19
    jom
    0.18
     desn
    0.18
    çŀ³
    0.18
    elsen
    0.17
    å¸ĺ
    0.17
    Activations Density 0.033%

    No Known Activations