© 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. 13663
    Prev
    Next
    INDEX
    Explanations

    fish, cucumber, source, tuna, concentrates

    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
    å¸ĮæľĽèĥ½å¤Ł
    -0.21
    erval
    -0.20
    æµģæ°´
    -0.19
    è¹ĩ
    -0.19
    shake
    -0.19
    åģĩæĹ¥
    -0.19
    quo
    -0.19
    水管
    -0.19
    igators
    -0.19
    nier
    -0.19
    POSITIVE LOGITS
    ç´ł
    0.20
    باء
    0.20
    æĭĪ
    0.20
    岬
    0.19
     calle
    0.19
    åIJĥè¿ĩ
    0.19
    æĹłæīĢ
    0.19
    ä¸ĢæĬĬ
    0.19
    гад
    0.18
    æĿĥå¨ģ
    0.18
    Activations Density 0.009%

    No Known Activations