© 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. 14327
    Prev
    Next
    INDEX
    Explanations

    <!-- or <?xml or 'use strict' or apparition or Solar electricity

    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
    ãĥ¼ãĥĹ
    -0.20
    å¸ĪåĤħ
    -0.19
    å¿ĸ
    -0.19
    inux
    -0.19
    åĥµ
    -0.19
    轻微
    -0.18
     Sage
    -0.18
     traded
    -0.18
    æĸĹå¿Ĺ
    -0.18
    é¦Ķ
    -0.18
    POSITIVE LOGITS
    迹
    0.20
    cai
    0.20
    åľ°çĤ¹
    0.20
    åij¶
    0.19
    åĭ
    0.19
    第ä¸ī代
    0.18
     tire
    0.18
    æ¯ĶåĪ©æŶ
    0.18
    site
    0.18
    skin
    0.18
    Activations Density 0.008%

    No Known Activations