© 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. 13339
    Prev
    Next
    INDEX
    Explanations

    interpretations of court cases

    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
    åħ³äºİæĪij们
    -0.21
    éĵ¡
    -0.20
     bure
    -0.19
    çģ¼
    -0.19
    ãĤªãĥ¼ãĥĹãĥ³
    -0.18
     elimin
    -0.18
    åı£ç¢ij
    -0.18
     plans
    -0.18
    æijĴ
    -0.18
    表æī¬
    -0.18
    POSITIVE LOGITS
     interpretations
    0.26
    ä¾Ŀæį®
    0.26
     Interpret
    0.23
    interpret
    0.23
    äºīè®®
    0.22
    æŃ£å½ĵ
    0.22
     interpretation
    0.22
    æĮīçħ§
    0.21
     Transitional
    0.21
    åIJĪæ³ķ
    0.21
    Activations Density 0.175%

    No Known Activations