© 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. 14406
    Prev
    Next
    INDEX
    Explanations

    loaded rotation

    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
    è¡Į为
    -0.25
    ä¸ĢåĪ»
    -0.24
    å½ķ
    -0.24
    ä¸įæĿ¥
    -0.22
    æĦŁè§¦
    -0.21
    è¨Ģè¡Į
    -0.21
    ç¼ł
    -0.21
    çļĦè¡Į为
    -0.21
    åIJİæĤĶ
    -0.20
    说èĩªå·±
    -0.20
    POSITIVE LOGITS
    éĺµå®¹
    0.28
    æķ´ä½ĵ
    0.25
     constellation
    0.25
    åĩij
    0.24
    åĽĬ
    0.23
     roster
    0.22
    æľīèĥ½åĬĽ
    0.22
    çĴľ
    0.21
    æĹ¢æľī
    0.21
    梯éĺŁ
    0.21
    Activations Density 0.029%

    No Known Activations