© 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. 13333
    Prev
    Next
    INDEX
    Explanations

    code syntax and punctuation

    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
     оÑĤкÑĢ
    -0.20
    æ´ĩ
    -0.19
    å¼Ģè¾Ł
    -0.19
    çªģ
    -0.19
    Ñĥж
    -0.19
     Nielsen
    -0.18
    å°¤
    -0.18
    äºĮæ°§åĮĸ
    -0.18
    å¤ĩ
    -0.18
    éķ¿æĺ¥
    -0.18
    POSITIVE LOGITS
    为客æĪ·
    0.19
     =",
    0.18
    åį°èĬ±
    0.17
    CodeAt
    0.17
     lect
    0.16
    æ¯ıéļĶ
    0.16
     Balance
    0.16
    hap
    0.16
    ãĥģãĥ£ãĥ³
    0.16
     Nug
    0.16
    Activations Density 1.544%

    No Known Activations