© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15372
    Prev
    Next
    INDEX
    Explanations

    lists of items connected by 'and'

    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
    ivery
    -0.22
    roach
    -0.19
    æĹ¶è¾°
    -0.18
    ãģ®ãĤĤ
    -0.18
    å¦Ļ
    -0.18
     Imaging
    -0.18
    æĹĥ
    -0.18
    wor
    -0.17
    åĿļå®ŀ
    -0.17
     lá»Ļ
    -0.17
    POSITIVE LOGITS
    以åıĬ
    0.52
    以åıĬåħ¶ä»ĸ
    0.40
     serta
    0.39
     sowie
    0.33
    ãģĬãĤĪãģ³
    0.30
    ãģĿãģĹãģ¦
    0.26
     ê·¸ë¦¬ê³ł
    0.25
     ainsi
    0.25
     oraz
    0.22
    åıĬ
    0.21
    Activations Density 0.246%

    No Known Activations