© 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. 11148
    Prev
    Next
    INDEX
    Explanations

    installment or sequel in a series

    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
    åįľ
    -0.20
    :///
    -0.20
    riad
    -0.19
    æĸ¹æĸ¹éĿ¢éĿ¢
    -0.19
     SV
    -0.18
    çĤ¹å¤ļ
    -0.18
    åģļæ³ķ
    -0.17
    åıĹä¸įäºĨ
    -0.17
    ikal
    -0.17
    èµĦæºIJä¼ĺåĬ¿
    -0.17
    POSITIVE LOGITS
    亲
    0.23
    unicode
    0.20
    ä½ĵ
    0.19
    森æŀĹåħ¬åĽŃ
    0.19
    bios
    0.19
    bs
    0.19
    åĪ»
    0.19
     fours
    0.18
    代
    0.18
     pivotal
    0.18
    Activations Density 0.045%

    No Known Activations