© 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. 12514
    Prev
    Next
    INDEX
    Explanations

    beer, ale, and brewing

    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
    éĽī
    -0.23
    æĸ°äºº
    -0.21
    riad
    -0.21
    éŁŃèıľ
    -0.20
    ãįī
    -0.19
    亲èĩª
    -0.19
    éĿ
    -0.19
    éĢ¼
    -0.19
    rst
    -0.19
    osi
    -0.19
    POSITIVE LOGITS
    ä¼łç»Ł
    0.24
    ç±»åŀĭ
    0.23
    åħ¸èĮĥ
    0.22
    åĩºåİĤ
    0.22
    Traditional
    0.22
    type
    0.22
    åģľäº§
    0.22
    tipo
    0.21
     tipo
    0.21
    åĤ³çµ±
    0.21
    Activations Density 0.007%

    No Known Activations