© 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. 13134
    Prev
    Next
    INDEX
    Explanations

    vacant abandoned property

    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
    éĺµå®¹
    -0.21
     Etsy
    -0.21
    æŃ£å®Ĺ
    -0.21
    åĪ¨
    -0.21
    çIJĽ
    -0.20
    èģª
    -0.19
    æľ¬ç½ij
    -0.19
    raphic
    -0.19
     GetComponent
    -0.19
    纨
    -0.18
    POSITIVE LOGITS
    空
    0.32
    æĹłäºº
    0.30
    æŧ
    0.26
    为空
    0.24
    éĹ²ç½®
    0.23
    没人
    0.23
    /un
    0.22
     hollow
    0.21
    åºŁå¼ĥ
    0.21
     Closed
    0.21
    Activations Density 0.036%

    No Known Activations