© 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. 12808
    Prev
    Next
    INDEX
    Explanations

    numbers after times

    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
    äºĨæĪijçļĦ
    -0.24
    æ®ĭéħ·
    -0.21
    ãģıãĤīãģĦ
    -0.20
     niche
    -0.20
    éĩijèŀįåį±æľº
    -0.20
    åĬłçĽŁ
    -0.19
     dictator
    -0.18
    ê°ĢëĬĶ
    -0.18
    åĨ¥
    -0.18
    Rejected
    -0.18
    POSITIVE LOGITS
    åħ¬åħ±æľįåĬ¡
    0.27
    æ©ŁéĹľ
    0.23
    åħ¬ä¼Ĺ
    0.23
    å®£ä¼łæķĻèĤ²
    0.23
    æľºåħ³
    0.23
    å·¡è§Ĩ
    0.22
    å·¥ä½ľäººåijĺ
    0.22
    åIJij社ä¼ļ
    0.22
    å¸Ĥæ°ij
    0.22
    åħ¬æ°ij
    0.21
    Activations Density 0.016%

    No Known Activations