© 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. 12251
    Prev
    Next
    INDEX
    Explanations

    bow tie or ribbon

    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
    gang
    -0.19
     Cruc
    -0.18
    æĺ
    -0.18
    å¼ŁåħĦ
    -0.18
    æ§ģ
    -0.18
    едÑĮ
    -0.18
    çģ¯çģ«
    -0.18
    iability
    -0.17
    .getItem
    -0.17
    æīĵéĢļ
    -0.17
    POSITIVE LOGITS
    åĦ¿
    0.28
    _queues
    0.21
    åħĴ
    0.20
    è®¤çľŁåŃ¦ä¹ł
    0.20
     blowing
    0.20
    ÑĤок
    0.20
    èĥ¸
    0.20
    驾
    0.20
    éĩįçĤ¹é¢ĨåŁŁ
    0.20
    åŀĤ
    0.19
    Activations Density 0.004%

    No Known Activations